Haotong Qin

Jiakai Wang, Zixin Yin, Pengfei Hu et al.

To operate in real-world high-stakes environments, deep learning systems have to endure noises that have been continuously thwarting their robustness. Data-end defense, which improves robustness by operations on input data instead of modifying models, has attracted intensive attention due to its feasibility in practice. However, previous data-end defenses show low generalization against diverse noises and weak transferability across multiple models. Motivated by the fact that robust recognition depends on both local and global features, we propose a defensive patch generation framework to address these problems by helping models better exploit these features. For the generalization against diverse noises, we inject class-specific identifiable patterns into a confined local patch prior, so that defensive patches could preserve more recognizable features towards specific classes, leading models for better recognition under noises. For the transferability across multiple models, we guide the defensive patches to capture more global feature correlations within a class, so that they could activate model-shared global perceptions and transfer better among models. Our defensive patches show great potentials to improve application robustness in practice by simply sticking them around target objects. Extensive experiments show that we outperform others by large margins (improve 20+\% accuracy for both adversarial and corruption robustness on average in the digital and physical world). Our codes are available at https://github.com/nlsde-safety-team/DefensivePatch

Haotong Qin, Ge-Peng Ji, Salman Khan et al.

Google's Bard has emerged as a formidable competitor to OpenAI's ChatGPT in the field of conversational AI. Notably, Bard has recently been updated to handle visual inputs alongside text prompts during conversations. Given Bard's impressive track record in handling textual inputs, we explore its capabilities in understanding and interpreting visual data (images) conditioned by text questions. This exploration holds the potential to unveil new insights and challenges for Bard and other forthcoming multi-modal Generative models, especially in addressing complex computer vision problems that demand accurate visual and language understanding. Specifically, in this study, we focus on 15 diverse task scenarios encompassing regular, camouflaged, medical, under-water and remote sensing data to comprehensively evaluate Bard's performance. Our primary finding indicates that Bard still struggles in these vision scenarios, highlighting the significant gap in vision-based understanding that needs to be bridged in future developments. We expect that this empirical study will prove valuable in advancing future models, leading to enhanced capabilities in comprehending and interpreting fine-grained visual data. Our project is released on https://github.com/htqin/GoogleBard-VisUnderstand

Haotong Qin, Mingyuan Zhang, Yifu Ding et al.

Network binarization emerges as one of the most promising compression approaches offering extraordinary computation and memory savings by minimizing the bit-width. However, recent research has shown that applying existing binarization algorithms to diverse tasks, architectures, and hardware in realistic scenarios is still not straightforward. Common challenges of binarization, such as accuracy degradation and efficiency limitation, suggest that its attributes are not fully understood. To close this gap, we present BiBench, a rigorously designed benchmark with in-depth analysis for network binarization. We first carefully scrutinize the requirements of binarization in the actual production and define evaluation tracks and metrics for a comprehensive and fair investigation. Then, we evaluate and analyze a series of milestone binarization algorithms that function at the operator level and with extensive influence. Our benchmark reveals that 1) the binarized operator has a crucial impact on the performance and deployability of binarized networks; 2) the accuracy of binarization varies significantly across different learning tasks and neural architectures; 3) binarization has demonstrated promising efficiency potential on edge devices despite the limited hardware support. The results and analysis also lead to a promising paradigm for accurate and efficient binarization. We believe that BiBench will contribute to the broader adoption of binarization and serve as a foundation for future research. The code for our BiBench is released https://github.com/htqin/BiBench .

Haotong Qin, Yifu Ding, Mingyuan Zhang et al.

The large pre-trained BERT has achieved remarkable performance on Natural Language Processing (NLP) tasks but is also computation and memory expensive. As one of the powerful compression approaches, binarization extremely reduces the computation and memory consumption by utilizing 1-bit parameters and bitwise operations. Unfortunately, the full binarization of BERT (i.e., 1-bit weight, embedding, and activation) usually suffer a significant performance drop, and there is rare study addressing this problem. In this paper, with the theoretical justification and empirical analysis, we identify that the severe performance drop can be mainly attributed to the information degradation and optimization direction mismatch respectively in the forward and backward propagation, and propose BiBERT, an accurate fully binarized BERT, to eliminate the performance bottlenecks. Specifically, BiBERT introduces an efficient Bi-Attention structure for maximizing representation information statistically and a Direction-Matching Distillation (DMD) scheme to optimize the full binarized BERT accurately. Extensive experiments show that BiBERT outperforms both the straightforward baseline and existing state-of-the-art quantized BERTs with ultra-low bit activations by convincing margins on the NLP benchmark. As the first fully binarized BERT, our method yields impressive 56.3 times and 31.2 times saving on FLOPs and model size, demonstrating the vast advantages and potential of the fully binarized BERT model in real-world resource-constrained scenarios.

Yifu Ding, Haotong Qin, Qinghua Yan et al.

Vision transformer emerges as a potential architecture for vision tasks. However, the intense computation and non-negligible delay hinder its application in the real world. As a widespread model compression technique, existing post-training quantization methods still cause severe performance drops. We find the main reasons lie in (1) the existing calibration metric is inaccurate in measuring the quantization influence for extremely low-bit representation, and (2) the existing quantization paradigm is unfriendly to the power-law distribution of Softmax. Based on these observations, we propose a novel Accurate Post-training Quantization framework for Vision Transformer, namely APQ-ViT. We first present a unified Bottom-elimination Blockwise Calibration scheme to optimize the calibration metric to perceive the overall quantization disturbance in a blockwise manner and prioritize the crucial quantization errors that influence more on the final output. Then, we design a Matthew-effect Preserving Quantization for Softmax to maintain the power-law character and keep the function of the attention mechanism. Comprehensive experiments on large-scale classification and detection datasets demonstrate that our APQ-ViT surpasses the existing post-training quantization methods by convincing margins, especially in lower bit-width settings (e.g., averagely up to 5.17% improvement for classification and 24.43% for detection on W4A4). We also highlight that APQ-ViT enjoys versatility and works well on diverse transformer variants.

Haotong Qin, Xudong Ma, Yifu Ding et al.

Deep neural networks, such as the Deep-FSMN, have been widely studied for keyword spotting (KWS) applications while suffering expensive computation and storage. Therefore, network compression technologies like binarization are studied to deploy KWS models on edge. In this paper, we present a strong yet efficient binary neural network for KWS, namely BiFSMNv2, pushing it to the real-network accuracy performance. First, we present a Dual-scale Thinnable 1-bit-Architecture to recover the representation capability of the binarized computation units by dual-scale activation binarization and liberate the speedup potential from an overall architecture perspective. Second, we also construct a Frequency Independent Distillation scheme for KWS binarization-aware training, which distills the high and low-frequency components independently to mitigate the information mismatch between full-precision and binarized representations. Moreover, we propose the Learning Propagation Binarizer, a general and efficient binarizer that enables the forward and backward propagation of binary KWS networks to be continuously improved through learning. We implement and deploy the BiFSMNv2 on ARMv8 real-world hardware with a novel Fast Bitwise Computation Kernel, which is proposed to fully utilize registers and increase instruction throughput. Comprehensive experiments show our BiFSMNv2 outperforms existing binary networks for KWS by convincing margins across different datasets and achieves comparable accuracy with the full-precision networks (only a tiny 1.51% drop on Speech Commands V1-12). We highlight that benefiting from the compact architecture and optimized hardware kernel, BiFSMNv2 can achieve an impressive 25.1x speedup and 20.2x storage-saving on edge hardware.

Yisong Xiao, Aishan Liu, Tianyuan Zhang et al.

Quantization has emerged as an essential technique for deploying deep neural networks (DNNs) on devices with limited resources. However, quantized models exhibit vulnerabilities when exposed to various noises in real-world applications. Despite the importance of evaluating the impact of quantization on robustness, existing research on this topic is limited and often disregards established principles of robustness evaluation, resulting in incomplete and inconclusive findings. To address this gap, we thoroughly evaluated the robustness of quantized models against various noises (adversarial attacks, natural corruptions, and systematic noises) on ImageNet. The comprehensive evaluation results empirically provide valuable insights into the robustness of quantized models in various scenarios, for example: (1) quantized models exhibit higher adversarial robustness than their floating-point counterparts, but are more vulnerable to natural corruptions and systematic noises; (2) in general, increasing the quantization bit-width results in a decrease in adversarial robustness, an increase in natural robustness, and an increase in systematic robustness; (3) among corruption methods, \textit{impulse noise} and \textit{glass blur} are the most harmful to quantized models, while \textit{brightness} has the least impact; (4) among systematic noises, the \textit{nearest neighbor interpolation} has the highest impact, while bilinear interpolation, cubic interpolation, and area interpolation are the three least harmful. Our research contributes to advancing the robust quantization of models and their deployment in real-world scenarios.

Ruihao Gong, Yifu Ding, Zining Wang et al.

Large language models (LLMs) have achieved remarkable advancements in natural language processing, showcasing exceptional performance across various tasks. However, the expensive memory and computational requirements present significant challenges for their practical deployment. Low-bit quantization has emerged as a critical approach to mitigate these challenges by reducing the bit-width of model parameters, activations, and gradients, thus decreasing memory usage and computational demands. This paper presents a comprehensive survey of low-bit quantization methods tailored for LLMs, covering the fundamental principles, system implementations, and algorithmic strategies. An overview of basic concepts and new data formats specific to low-bit LLMs is first introduced, followed by a review of frameworks and systems that facilitate low-bit LLMs across various hardware platforms. Then, we categorize and analyze techniques and toolkits for efficient low-bit training and inference of LLMs. Finally, we conclude with a discussion of future trends and potential advancements of low-bit LLMs. Our systematic overview from basic, system, and algorithm perspectives can offer valuable insights and guidelines for future works to enhance the efficiency and applicability of LLMs through low-bit quantization.

Wei Huang, Yangdong Liu, Haotong Qin et al.

Pretrained large language models (LLMs) exhibit exceptional general language processing capabilities but come with significant demands on memory and computational resources. As a powerful compression technology, binarization can extremely reduce model weights to a mere 1 bit, lowering the expensive computation and memory requirements. However, existing quantization techniques fall short of maintaining LLM performance under ultra-low bit-widths. In response to this challenge, we present BiLLM, a groundbreaking 1-bit post-training quantization scheme tailored for pretrained LLMs. Based on the weight distribution of LLMs, BiLLM first identifies and structurally selects salient weights, and minimizes the compression loss through an effective binary residual approximation strategy. Moreover, considering the bell-shaped distribution of the non-salient weights, we propose an optimal splitting search to group and binarize them accurately. BiLLM achieving for the first time high-accuracy inference (e.g. 8.41 perplexity on LLaMA2-70B) with only 1.08-bit weights across various LLMs families and evaluation metrics, outperforms SOTA quantization methods of LLM by significant margins. Moreover, BiLLM enables the binarization process of the LLM with 7 billion weights within 0.5 hours on a single GPU, demonstrating satisfactory time efficiency. Our code is available at https://github.com/Aaronhuang-778/BiLLM.

Wei Huang, Haotong Qin, Yangdong Liu et al.

Low-bit quantization emerges as one of the most promising compression approaches for deploying deep neural networks on edge devices. Mixed-precision quantization leverages a mixture of bit-widths to unleash the accuracy and efficiency potential of quantized models. However, existing mixed-precision quantization methods rely on simulations in high-performance devices to achieve accuracy and efficiency trade-offs in immense search spaces. This leads to a non-negligible gap between the estimated efficiency metrics and the actual hardware that makes quantized models far away from the optimal accuracy and efficiency, and also causes the quantization process to rely on additional high-performance devices. In this paper, we propose an On-Chip Hardware-Aware Quantization (OHQ) framework, performing hardware-aware mixed-precision quantization on deployed edge devices to achieve accurate and efficient computing. Specifically, for efficiency metrics, we built an On-Chip Quantization Aware pipeline, which allows the quantization process to perceive the actual hardware efficiency of the quantization operator and avoid optimization errors caused by inaccurate simulation. For accuracy metrics, we propose Mask-Guided Quantization Estimation technology to effectively estimate the accuracy impact of operators in the on-chip scenario, getting rid of the dependence of the quantization process on high computing power. By synthesizing insights from quantized models and hardware through linear optimization, we can obtain optimized bit-width configurations to achieve outstanding performance on accuracy and efficiency. We evaluate inference accuracy and acceleration with quantization for various architectures and compression ratios on hardware. OHQ achieves 70% and 73% accuracy for ResNet-18 and MobileNetV3, respectively, and can reduce latency by 15~30% compared to INT8 on real deployment.

Yisong Xiao, Tianyuan Zhang, Shunchang Liu et al.

Quantization has emerged as an essential technique for deploying deep neural networks (DNNs) on devices with limited resources. However, quantized models exhibit vulnerabilities when exposed to various noises in real-world applications. Despite the importance of evaluating the impact of quantization on robustness, existing research on this topic is limited and often disregards established principles of robustness evaluation, resulting in incomplete and inconclusive findings. To address this gap, we thoroughly evaluated the robustness of quantized models against various noises (adversarial attacks, natural corruptions, and systematic noises) on ImageNet. Extensive experiments demonstrate that lower-bit quantization is more resilient to adversarial attacks but is more susceptible to natural corruptions and systematic noises. Notably, our investigation reveals that impulse noise (in natural corruptions) and the nearest neighbor interpolation (in systematic noises) have the most significant impact on quantized models. Our research contributes to advancing the robust quantization of models and their deployment in real-world scenarios.

Haotong Qin, Xudong Ma, Xingyu Zheng et al.

The LoRA-finetuning quantization of LLMs has been extensively studied to obtain accurate yet compact LLMs for deployment on resource-constrained hardware. However, existing methods cause the quantized LLM to severely degrade and even fail to benefit from the finetuning of LoRA. This paper proposes a novel IR-QLoRA for pushing quantized LLMs with LoRA to be highly accurate through information retention. The proposed IR-QLoRA mainly relies on two technologies derived from the perspective of unified information: (1) statistics-based Information Calibration Quantization allows the quantized parameters of LLM to retain original information accurately; (2) finetuning-based Information Elastic Connection makes LoRA utilizes elastic representation transformation with diverse information. Comprehensive experiments show that IR-QLoRA can significantly improve accuracy across LLaMA and LLaMA2 families under 2-4 bit-widths, e.g., 4- bit LLaMA-7B achieves 1.4% improvement on MMLU compared with the state-of-the-art methods. The significant performance gain requires only a tiny 0.31% additional time consumption, revealing the satisfactory efficiency of our IR-QLoRA. We highlight that IR-QLoRA enjoys excellent versatility, compatible with various frameworks (e.g., NormalFloat and Integer quantization) and brings general accuracy gains. The code is available at https://github.com/htqin/ir-qlora.

Wei Huang, Xingyu Zheng, Xudong Ma et al.

The LLaMA family, a collection of foundation language models ranging from 7B to 65B parameters, has become one of the most powerful open-source large language models (LLMs) and the popular LLM backbone of multi-modal large language models (MLLMs), widely used in computer vision and natural language understanding tasks. In particular, LLaMA3 models have recently been released and have achieved impressive performance in various domains with super-large scale pre-training on over 15T tokens of data. Given the wide application of low-bit quantization for LLMs in resource-constrained scenarios, we explore LLaMA3's capabilities when quantized to low bit-width. This exploration can potentially provide new insights and challenges for the low-bit quantization of LLaMA3 and other future LLMs, especially in addressing performance degradation issues that suffer in LLM compression. Specifically, we comprehensively evaluate the 10 existing post-training quantization and LoRA fine-tuning (LoRA-FT) methods of LLaMA3 on 1-8 bits and various datasets to reveal the low-bit quantization performance of LLaMA3. To uncover the capabilities of low-bit quantized MLLM, we assessed the performance of the LLaMA3-based LLaVA-Next-8B model under 2-4 ultra-low bits with post-training quantization methods. Our experimental results indicate that LLaMA3 still suffers from non-negligible degradation in linguistic and visual contexts, particularly under ultra-low bit widths. This highlights the significant performance gap at low bit-width that needs to be addressed in future developments. We expect that this empirical study will prove valuable in advancing future models, driving LLMs and MLLMs to achieve higher accuracy at lower bit to enhance practicality. Our project is released on https://github.com/Macaronlin/LLaMA3-Quantization , and quantized models are released at https://huggingface.co/Efficient-ML .

Zixiang Zhao, Lilun Deng, Haowen Bai et al.

Image fusion integrates essential information from multiple images into a single composite, enhancing structures, textures, and refining imperfections. Existing methods predominantly focus on pixel-level and semantic visual features for recognition, but often overlook the deeper text-level semantic information beyond vision. Therefore, we introduce a novel fusion paradigm named image Fusion via vIsion-Language Model (FILM), for the first time, utilizing explicit textual information from source images to guide the fusion process. Specifically, FILM generates semantic prompts from images and inputs them into ChatGPT for comprehensive textual descriptions. These descriptions are fused within the textual domain and guide the visual information fusion, enhancing feature extraction and contextual understanding, directed by textual semantic information via cross-attention. FILM has shown promising results in four image fusion tasks: infrared-visible, medical, multi-exposure, and multi-focus image fusion. We also propose a vision-language dataset containing ChatGPT-generated paragraph descriptions for the eight image fusion datasets across four fusion tasks, facilitating future research in vision-language model-based image fusion. Code and dataset are available at https://github.com/Zhaozixiang1228/IF-FILM.

Hong Chen, Chengtao Lv, Liang Ding et al.

Large language models (LLMs) have significantly advanced the field of natural language processing, while the expensive memory and computation consumption impede their practical deployment. Quantization emerges as one of the most effective methods for improving the computational efficiency of LLMs. However, existing ultra-low-bit quantization always causes severe accuracy drops. In this paper, we empirically relieve the micro and macro characteristics of ultra-low bit quantization and present a novel Dual-Binarization method for LLMs, namely DB-LLM. For the micro-level, we take both the accuracy advantage of 2-bit-width and the efficiency advantage of binarization into account, introducing Flexible Dual Binarization (FDB). By splitting 2-bit quantized weights into two independent sets of binaries, FDB ensures the accuracy of representations and introduces flexibility, utilizing the efficient bitwise operations of binarization while retaining the inherent high sparsity of ultra-low bit quantization. For the macro-level, we find the distortion that exists in the prediction of LLM after quantization, which is specified as the deviations related to the ambiguity of samples. We propose the Deviation-Aware Distillation (DAD) method, enabling the model to focus differently on various samples. Comprehensive experiments show that our DB-LLM not only significantly surpasses the current State-of-The-Art (SoTA) in ultra-low bit quantization (eg, perplexity decreased from 9.64 to 7.23), but also achieves an additional 20\% reduction in computational consumption compared to the SOTA method under the same bit-width. Our code will be released soon.

Wei Huang, Haotong Qin, Yangdong Liu et al.

Post-training quantization (PTQ) is an effective technique for compressing large language models (LLMs). However, while uniform-precision quantization is computationally efficient, it often compromises model performance. To address this, we propose SliM-LLM, a salience-driven mixed-precision quantization framework that allocates bit-widths at the group-wise. Our approach leverages the observation that important weights follow a structured distribution and introduces two key components: \textbf{1)} \textit{Salience-Determined Bit Allocation} adaptively assigns bit-widths to groups within each layer based on their salience; and \textbf{2)} \textit{Salience-Weighted Quantizer Calibration} optimizes quantizer parameters by incorporating element-level salience. With its structured partitioning, SliM-LLM provides a hardware-friendly solution that matches the efficiency of uniform quantization methods while improving accuracy. Experiments show that SliM-LLM achieves superior performance across various LLMs at low bit-widths. For example, a 2-bit quantized LLaMA-7B model reduces memory usage by nearly 6x compared to the floating-point baseline, decreases perplexity by 48\% compared to state-of-the-art gradient-free PTQ methods, and maintains GPU inference speed. Additionally, the extended version, SliM-LLM$^+$, which incorporates gradient-based quantization, further reduces perplexity by 35.1\%. Our code is available at https://github.com/Aaronhuang-778/SliM-LLM

Zhiteng Li, Yulun Zhang, Jing Lin et al.

3D human pose and shape estimation (HPE) aims to reconstruct the 3D human body, face, and hands from a single image. Although powerful deep learning models have achieved accurate estimation in this task, they require enormous memory and computational resources. Consequently, these methods can hardly be deployed on resource-limited edge devices. In this work, we propose BinaryHPE, a novel binarization method designed to estimate the 3D human body, face, and hands parameters efficiently. Specifically, we propose a novel binary backbone called Binarized Dual Residual Network (BiDRN), designed to retain as much full-precision information as possible. Furthermore, we propose the Binarized BoxNet, an efficient sub-network for predicting face and hands bounding boxes, which further reduces model redundancy. Comprehensive quantitative and qualitative experiments demonstrate the effectiveness of BinaryHPE, which has a significant improvement over state-of-the-art binarization algorithms. Moreover, our BinaryHPE achieves comparable performance with the full-precision method Hand4Whole while using only 22.1% parameters and 14.8% operations. We will release all the code and pretrained models.

Ge Yang, Changyi He, Jinyang Guo et al.

Although large language models (LLMs) have demonstrated their strong intelligence ability, the high demand for computation and storage hinders their practical application. To this end, many model compression techniques are proposed to increase the efficiency of LLMs. However, current researches only validate their methods on limited models, datasets, metrics, etc, and still lack a comprehensive evaluation under more general scenarios. So it is still a question of which model compression approach we should use under a specific case. To mitigate this gap, we present the Large Language Model Compression Benchmark (LLMCBench), a rigorously designed benchmark with an in-depth analysis for LLM compression algorithms. We first analyze the actual model production requirements and carefully design evaluation tracks and metrics. Then, we conduct extensive experiments and comparison using multiple mainstream LLM compression approaches. Finally, we perform an in-depth analysis based on the evaluation and provide useful insight for LLM compression design. We hope our LLMCBench can contribute insightful suggestions for LLM compression algorithm design and serve as a foundation for future research. Our code is available at https://github.com/AboveParadise/LLMCBench.

Mingyi Zhang, Cheng Hu, Yiqin Wang et al.

High-speed multi-agent autonomous racing demands robust spatiotemporal planning and precise control under strict computational limits. Current methods often oversimplify interactions or abandon strict kinematic constraints. We resolve this by proposing a Topological Gap Identification and Accelerated MPC framework. By predicting opponent behaviors via SGPs, our method constructs dynamic occupancy corridors to robustly select optimal overtaking gaps. We ensure strict kinematic feasibility using a Linear Time-Varying MPC powered by a customized Pseudo-Transient Continuation (PTC) solver for high-frequency execution. Experimental results on the F1TENTH platform show that our method significantly outperforms state-of-the-art baselines: it reduces total maneuver time by 51.6% in sequential scenarios, consistently maintains an overtaking success rate exceeding 81% in dense bottlenecks, and lowers average computational latency by 20.3%, pushing the boundaries of safe and high-speed autonomous racing.

Weilun Feng, Chuanguang Yang, Haotong Qin et al.

Diffusion transformers (DiT) have demonstrated exceptional performance in video generation. However, their large number of parameters and high computational complexity limit their deployment on edge devices. Quantization can reduce storage requirements and accelerate inference by lowering the bit-width of model parameters. Yet, existing quantization methods for image generation models do not generalize well to video generation tasks. We identify two primary challenges: the loss of information during quantization and the misalignment between optimization objectives and the unique requirements of video generation. To address these challenges, we present Q-VDiT, a quantization framework specifically designed for video DiT models. From the quantization perspective, we propose the Token-aware Quantization Estimator (TQE), which compensates for quantization errors in both the token and feature dimensions. From the optimization perspective, we introduce Temporal Maintenance Distillation (TMD), which preserves the spatiotemporal correlations between frames and enables the optimization of each frame with respect to the overall video context. Our W3A6 Q-VDiT achieves a scene consistency of 23.40, setting a new benchmark and outperforming current state-of-the-art quantization methods by 1.9$\times$. Code will be available at https://github.com/cantbebetter2/Q-VDiT.

Xingyu Zheng, Xianglong Liu, Yichen Bian et al.

Diffusion models (DMs) have been significantly developed and widely used in various applications due to their excellent generative qualities. However, the expensive computation and massive parameters of DMs hinder their practical use in resource-constrained scenarios. As one of the effective compression approaches, quantization allows DMs to achieve storage saving and inference acceleration by reducing bit-width while maintaining generation performance. However, as the most extreme quantization form, 1-bit binarization causes the generation performance of DMs to face severe degradation or even collapse. This paper proposes a novel method, namely BiDM, for fully binarizing weights and activations of DMs, pushing quantization to the 1-bit limit. From a temporal perspective, we introduce the Timestep-friendly Binary Structure (TBS), which uses learnable activation binarizers and cross-timestep feature connections to address the highly timestep-correlated activation features of DMs. From a spatial perspective, we propose Space Patched Distillation (SPD) to address the difficulty of matching binary features during distillation, focusing on the spatial locality of image generation tasks and noise estimation networks. As the first work to fully binarize DMs, the W1A1 BiDM on the LDM-4 model for LSUN-Bedrooms 256$\times$256 achieves a remarkable FID of 22.74, significantly outperforming the current state-of-the-art general binarization methods with an FID of 59.44 and invalid generative samples, and achieves up to excellent 28.0 times storage and 52.7 times OPs savings. The code is available at https://github.com/Xingyu-Zheng/BiDM .

Xingyu Zheng, Xianglong Liu, Haotong Qin et al.

With the advancement of diffusion models (DMs) and the substantially increased computational requirements, quantization emerges as a practical solution to obtain compact and efficient low-bit DMs. However, the highly discrete representation leads to severe accuracy degradation, hindering the quantization of diffusion models to ultra-low bit-widths. This paper proposes a novel weight binarization approach for DMs, namely BinaryDM, pushing binarized DMs to be accurate and efficient by improving the representation and optimization. From the representation perspective, we present an Evolvable-Basis Binarizer (EBB) to enable a smooth evolution of DMs from full-precision to accurately binarized. EBB enhances information representation in the initial stage through the flexible combination of multiple binary bases and applies regularization to evolve into efficient single-basis binarization. The evolution only occurs in the head and tail of the DM architecture to retain the stability of training. From the optimization perspective, a Low-rank Representation Mimicking (LRM) is applied to assist the optimization of binarized DMs. The LRM mimics the representations of full-precision DMs in low-rank space, alleviating the direction ambiguity of the optimization process caused by fine-grained alignment. Comprehensive experiments demonstrate that BinaryDM achieves significant accuracy and efficiency gains compared to SOTA quantization methods of DMs under ultra-low bit-widths. With 1-bit weight and 4-bit activation (W1A4), BinaryDM achieves as low as 7.74 FID and saves the performance from collapse (baseline FID 10.87). As the first binarization method for diffusion models, W1A4 BinaryDM achieves impressive 15.2x OPs and 29.2x model size savings, showcasing its substantial potential for edge deployment. The code is available at https://github.com/Xingyu-Zheng/BinaryDM.

Libo Zhu, Jianze Li, Haotong Qin et al.

Diffusion-based image super-resolution (SR) models have shown superior performance at the cost of multiple denoising steps. However, even though the denoising step has been reduced to one, they require high computational costs and storage requirements, making it difficult for deployment on hardware devices. To address these issues, we propose a novel post-training quantization approach with adaptive scale in one-step diffusion (OSD) image SR, PassionSR. First, we simplify OSD model to two core components, UNet and Variational Autoencoder (VAE) by removing the CLIPEncoder. Secondly, we propose Learnable Boundary Quantizer (LBQ) and Learnable Equivalent Transformation (LET) to optimize the quantization process and manipulate activation distributions for better quantization. Finally, we design a Distributed Quantization Calibration (DQC) strategy that stabilizes the training of quantized parameters for rapid convergence. Comprehensive experiments demonstrate that PassionSR with 8-bit and 6-bit obtains comparable visual results with full-precision model. Moreover, our PassionSR achieves significant advantages over recent leading low-bit quantization methods for image SR. Our code will be at https://github.com/libozhu03/PassionSR.

Kai Liu, Qian Zheng, Kaiwen Tao et al.

With unprecedented rapid development, deep neural networks (DNNs) have deeply influenced almost all fields. However, their heavy computation costs and model sizes are usually unacceptable in real-world deployment. Model quantization, an effective weight-lighting technique, has become an indispensable procedure in the whole deployment pipeline. The essence of quantization acceleration is the conversion from continuous floating-point numbers to discrete integer ones, which significantly speeds up the memory I/O and calculation, i.e., addition and multiplication. However, performance degradation also comes with the conversion because of the loss of precision. Therefore, it has become increasingly popular and critical to investigate how to perform the conversion and how to compensate for the information loss. This article surveys the recent five-year progress towards low-bit quantization on DNNs. We discuss and compare the state-of-the-art quantization methods and classify them into 8 main categories and 24 sub-categories according to their core techniques. Furthermore, we shed light on the potential research opportunities in the field of model quantization. A curated list of model quantization is provided at https://github.com/Kai-Liu001/Awesome-Model-Quantization.

Xianglong Yan, Zhiteng Li, Tianao Zhang et al.

Large language models (LLMs) have demonstrated remarkable performance, but their long-context reasoning remains constrained by the excessive memory required for the Key-Value (KV) cache. This makes KV cache compression a critical step toward efficient long-context inference. Recent methods have explored low-rank techniques to reduce the hidden size of the KV cache. However, they neglect the distinct roles and varying importance of Keys and Values, leading to significant performance drops under high compression. To address this, we propose ReCalKV, a post-training low-rank KV cache compression approach with tailored strategies for Keys and Values. For Keys, we propose Head-wise Similarity aware Reordering (HSR), which clusters structurally similar heads into groups, enabling more accurate low-rank approximation via grouped SVD. For Values, we propose Offline Value Calibration (OVC), which efficiently calibrates the value projection matrix using calibration data without training, ensuring an accurate representation of contextual information. Extensive experiments show that ReCalKV consistently outperforms existing low-rank compression methods, achieving high compression ratios with minimal performance loss. The code and models will be available at:https://github.com/XIANGLONGYAN/ReCalKV.

Manyi Li, Renshuai Tao, Yufan Liu et al.

With the rapid advancement of deep learning, particularly through generative adversarial networks (GANs) and diffusion models (DMs), AI-generated images, or ``deepfakes", have become nearly indistinguishable from real ones. These images are widely shared across Online Social Networks (OSNs), raising concerns about their misuse. Existing deepfake detection methods overlook the ``block effects" introduced by compression in OSNs, which obscure deepfake artifacts, and primarily focus on raw images, rarely encountered in real-world scenarios. To address these challenges, we propose PLADA (Pay Less Attention to Deceptive Artifacts), a novel framework designed to tackle the lack of paired data and the ineffective use of compressed images. PLADA consists of two core modules: Block Effect Eraser (B2E), which uses a dual-stage attention mechanism to handle block effects, and Open Data Aggregation (ODA), which processes both paired and unpaired data to improve detection. Extensive experiments across 26 datasets demonstrate that PLADA achieves a remarkable balance in deepfake detection, outperforming SoTA methods in detecting deepfakes on OSNs, even with limited paired data and compression. More importantly, this work introduces the ``block effect" as a critical factor in deepfake detection, providing a robust solution for open-world scenarios. Our code is available at https://github.com/ManyiLee/PLADA.

Xin Ding, Xin Li, Haotong Qin et al.

Quantization and cache mechanisms are typically applied individually for efficient Diffusion Transformers (DiTs), each demonstrating notable potential for acceleration. However, the promoting effect of combining the two mechanisms on efficient generation remains under-explored. Through empirical investigation, we find that the combination of quantization and cache mechanisms for DiT is not straightforward, and two key challenges lead to severe catastrophic performance degradation: (i) the sample efficacy of calibration datasets in post-training quantization (PTQ) is significantly eliminated by cache operation; (ii) the combination of the above mechanisms introduces more severe exposure bias within sampling distribution, resulting in amplified error accumulation in the image generation process. In this work, we take advantage of these two acceleration mechanisms and propose a hybrid acceleration method by tackling the above challenges, aiming to further improve the efficiency of DiTs while maintaining excellent generation capability. Concretely, a temporal-aware parallel clustering (TAP) is designed to dynamically improve the sample selection efficacy for the calibration within PTQ for different diffusion steps. A variance compensation (VC) strategy is derived to correct the sampling distribution. It mitigates exposure bias through an adaptive correction factor generation. Extensive experiments have shown that our method has accelerated DiTs by 12.7x while preserving competitive generation capability. The code will be available at https://github.com/xinding-sys/Quant-Cache.

Kaicheng Yang, Xun Zhang, Haotong Qin et al.

Diffusion Transformers (DiTs) have recently emerged as a powerful backbone for image generation, demonstrating superior scalability and performance over U-Net architectures. However, their practical deployment is hindered by substantial computational and memory costs. While Quantization-Aware Training (QAT) has shown promise for U-Nets, its application to DiTs faces unique challenges, primarily due to the sensitivity and distributional complexity of activations. In this work, we identify activation quantization as the primary bottleneck for pushing DiTs to extremely low-bit settings. To address this, we propose a systematic QAT framework for DiTs, named RobuQ. We start by establishing a strong ternary weight (W1.58A4) DiT baseline. Building upon this, we propose RobustQuantizer to achieve robust activation quantization. Our theoretical analyses show that the Hadamard transform can convert unknown per-token distributions into per-token normal distributions, providing a strong foundation for this method. Furthermore, we propose AMPN, the first Activation-only Mixed-Precision Network pipeline for DiTs. This method applies ternary weights across the entire network while allocating different activation precisions to each layer to eliminate information bottlenecks. Through extensive experiments on unconditional and conditional image generation, our RobuQ framework achieves state-of-the-art performance for DiT quantization in sub-4-bit quantization configuration. To the best of our knowledge, RobuQ is the first achieving stable and competitive image generation on large datasets like ImageNet-1K with activations quantized to average 2 bits. The code and models will be available at https://github.com/racoonykc/RobuQ .

Tianao Zhang, Zhiteng Li, Xianglong Yan et al.

Diffusion large language models (dLLMs), which offer bidirectional context and flexible masked-denoising generation, are emerging as a compelling alternative to autoregressive (AR) LLMs. However, like AR LLMs, their model sizes continue to grow, motivating weight compression for deployment. Although post-training quantization (PTQ) is effective for AR LLMs, directly transferring it to dLLMs at 2-bit leads to unsatisfactory performance. To tackle these challenges, we propose Quant-dLLM, an ultra-low-bit PTQ framework tailored to dLLMs. Since masked-denoising activations in dLLMs differ from the fully visible signals assumed by standard PTQ methods, we introduce Masked Calibration Simulation (MCS) to align calibration with the timestep-dependent masking, which yields more reliable calibrations. Moreover, we propose a Data-aware Any-order Quantizer (DAQ) that learns ultra-low-bit weight representations via an optimization algorithm. It performs iterative approximation guided by our simulated calibration data. In addition, under a strict 2-bit budget, we introduce Adaptive Blockwise Mixed Precision (ABMP), a sensitivity-based precision allocation scheme that adaptively assigns bit width across channel groups. When restricted to 2-bit precision, Quant-dLLM consistently achieves higher accuracy than state-of-the-art (SOTA) AR-transfer PTQ methods on dLLMs. The code and models will be available at: https://github.com/ZTA2785/Quant-dLLM.

Xianglong Yan, Chengzhu Bao, Zhiteng Li et al.

Large Language Models (LLMs) have shown impressive capabilities across diverse tasks, but their large memory and compute demands hinder deployment. Ternarization has gained attention as a promising compression technique, delivering substantial size reduction and high computational efficiency. However, its potential in the post-training quantization (PTQ) setting remains underexplored, due to the challenge of training-free parameter optimization and the quantization difficulty posed by outliers and dispersed weights. To address these issues, we propose PT$^2$-LLM, a post-training ternarization framework tailored for LLMs. At its core is an Asymmetric Ternary Quantizer equipped with a two-stage refinement pipeline: (1) Iterative Ternary Fitting (ITF), which alternates between optimal ternary grid construction and flexible rounding to minimize quantization error, and (2) Activation-aware Grid Alignment (AGA), which further refines the ternary grid to better match full-precision outputs. In addition, we propose a plug-and-play Structural Similarity-based Reordering (SSR) strategy that leverages inter-column structural similarity to ease quantization and mitigate outlier effects, further enhancing overall performance. Extensive experiments demonstrate that PT$^2$-LLM delivers competitive performance against state-of-the-art (SOTA) 2-bit PTQ methods with lower memory cost, while also accelerating both prefill and decoding to achieve end-to-end speedup. The code and models will be available at https://github.com/XIANGLONGYAN/PT2-LLM.

Jiatong Li, Libo Zhu, Haotong Qin et al.

Diffusion models have been achieving remarkable performance in face restoration. However, the heavy computations of diffusion models make it difficult to deploy them on devices like smartphones. In this work, we propose QuantFace, a novel low-bit quantization for one-step diffusion face restoration models, where the full-precision (\ie, 32-bit) weights and activations are quantized to 4$\sim$6-bit. We first analyze the data distribution within activations and find that they are highly variant. To preserve the original data information, we employ rotation-scaling channel balancing. Furthermore, we propose Quantization-Distillation Low-Rank Adaptation (QD-LoRA) that jointly optimizes for quantization and distillation performance. Finally, we propose an adaptive bit-width allocation strategy. We formulate such a strategy as an integer programming problem, which combines quantization error and perceptual metrics to find a satisfactory resource allocation. Extensive experiments on the synthetic and real-world datasets demonstrate the effectiveness of QuantFace under 6-bit and 4-bit. QuantFace achieves significant advantages over recent leading low-bit quantization methods for face restoration. The code is available at https://github.com/jiatongli2024/QuantFace.

Kai Liu, Haotong Qin, Yong Guo et al.

Low-bit quantization has become widespread for compressing image super-resolution (SR) models for edge deployment, which allows advanced SR models to enjoy compact low-bit parameters and efficient integer/bitwise constructions for storage compression and inference acceleration, respectively. However, it is notorious that low-bit quantization degrades the accuracy of SR models compared to their full-precision (FP) counterparts. Despite several efforts to alleviate the degradation, the transformer-based SR model still suffers severe degradation due to its distinctive activation distribution. In this work, we present a dual-stage low-bit post-training quantization (PTQ) method for image super-resolution, namely 2DQuant, which achieves efficient and accurate SR under low-bit quantization. The proposed method first investigates the weight and activation and finds that the distribution is characterized by coexisting symmetry and asymmetry, long tails. Specifically, we propose Distribution-Oriented Bound Initialization (DOBI), using different searching strategies to search a coarse bound for quantizers. To obtain refined quantizer parameters, we further propose Distillation Quantization Calibration (DQC), which employs a distillation approach to make the quantized model learn from its FP counterpart. Through extensive experiments on different bits and scaling factors, the performance of DOBI can reach the state-of-the-art (SOTA) while after stage two, our method surpasses existing PTQ in both metrics and visual effects. 2DQuant gains an increase in PSNR as high as 4.52dB on Set5 (x2) compared with SOTA when quantized to 2-bit and enjoys a 3.60x compression ratio and 5.08x speedup ratio. The code and models will be available at https://github.com/Kai-Liu001/2DQuant.

Zheng Chen, Haotong Qin, Yong Guo et al.

Advanced diffusion models (DMs) perform impressively in image super-resolution (SR), but the high memory and computational costs hinder their deployment. Binarization, an ultra-compression algorithm, offers the potential for effectively accelerating DMs. Nonetheless, due to the model structure and the multi-step iterative attribute of DMs, existing binarization methods result in significant performance degradation. In this paper, we introduce a novel binarized diffusion model, BI-DiffSR, for image SR. First, for the model structure, we design a UNet architecture optimized for binarization. We propose the consistent-pixel-downsample (CP-Down) and consistent-pixel-upsample (CP-Up) to maintain dimension consistent and facilitate the full-precision information transfer. Meanwhile, we design the channel-shuffle-fusion (CS-Fusion) to enhance feature fusion in skip connection. Second, for the activation difference across timestep, we design the timestep-aware redistribution (TaR) and activation function (TaA). The TaR and TaA dynamically adjust the distribution of activations based on different timesteps, improving the flexibility and representation alability of the binarized module. Comprehensive experiments demonstrate that our BI-DiffSR outperforms existing binarization methods. Code is released at: https://github.com/zhengchen1999/BI-DiffSR.

Jinyan Hou, Shan Liu, Ya Zhang et al.

Graph neural networks (GNNs) have been widely applied in traffic demand prediction, and transportation modes can be divided into station-based mode and free-floating traffic mode. Existing research in traffic graph construction primarily relies on map matching to construct graphs based on the road network. However, the complexity and inhomogeneity of data distribution in free-floating traffic demand forecasting make road network matching inflexible. To tackle these challenges, this paper introduces a novel graph construction method tailored to free-floating traffic mode. We propose a novel density-based clustering algorithm (HDPC-L) to determine the flexible positioning of nodes in the graph, overcoming the computational bottlenecks of traditional clustering algorithms and enabling effective handling of large-scale datasets. Furthermore, we extract valuable information from ridership data to initialize the edge weights of GNNs. Comprehensive experiments on two real-world datasets, the Shenzhen bike-sharing dataset and the Haikou ride-hailing dataset, show that the method significantly improves the performance of the model. On average, our models show an improvement in accuracy of around 25\% and 19.5\% on the two datasets. Additionally, it significantly enhances computational efficiency, reducing training time by approximately 12% and 32.5% on the two datasets. We make our code available at https://github.com/houjinyan/HDPC-L-ODInit.

Haotong Qin, Xudong Ma, Yifu Ding et al.

The deep neural networks, such as the Deep-FSMN, have been widely studied for keyword spotting (KWS) applications. However, computational resources for these networks are significantly constrained since they usually run on-call on edge devices. In this paper, we present BiFSMN, an accurate and extreme-efficient binary neural network for KWS. We first construct a High-frequency Enhancement Distillation scheme for the binarization-aware training, which emphasizes the high-frequency information from the full-precision network's representation that is more crucial for the optimization of the binarized network. Then, to allow the instant and adaptive accuracy-efficiency trade-offs at runtime, we also propose a Thinnable Binarization Architecture to further liberate the acceleration potential of the binarized network from the topology perspective. Moreover, we implement a Fast Bitwise Computation Kernel for BiFSMN on ARMv8 devices which fully utilizes registers and increases instruction throughput to push the limit of deployment efficiency. Extensive experiments show that BiFSMN outperforms existing binarization methods by convincing margins on various datasets and is even comparable with the full-precision counterpart (e.g., less than 3% drop on Speech Commands V1-12). We highlight that benefiting from the thinnable architecture and the optimized 1-bit implementation, BiFSMN can achieve an impressive 22.3x speedup and 15.5x storage-saving on real-world edge hardware. Our code is released at https://github.com/htqin/BiFSMN.

Weilun Feng, Haotong Qin, Chuanguang Yang et al.

Diffusion models have received wide attention in generation tasks. However, the expensive computation cost prevents the application of diffusion models in resource-constrained scenarios. Quantization emerges as a practical solution that significantly saves storage and computation by reducing the bit-width of parameters. However, the existing quantization methods for diffusion models still cause severe degradation in performance, especially under extremely low bit-widths (2-4 bit). The primary decrease in performance comes from the significant discretization of activation values at low bit quantization. Too few activation candidates are unfriendly for outlier significant weight channel quantization, and the discretized features prevent stable learning over different time steps of the diffusion model. This paper presents MPQ-DM, a Mixed-Precision Quantization method for Diffusion Models. The proposed MPQ-DM mainly relies on two techniques:(1) To mitigate the quantization error caused by outlier severe weight channels, we propose an Outlier-Driven Mixed Quantization (OMQ) technique that uses $Kurtosis$ to quantify outlier salient channels and apply optimized intra-layer mixed-precision bit-width allocation to recover accuracy performance within target efficiency.(2) To robustly learn representations crossing time steps, we construct a Time-Smoothed Relation Distillation (TRD) scheme between the quantized diffusion model and its full-precision counterpart, transferring discrete and continuous latent to a unified relation space to reduce the representation inconsistency. Comprehensive experiments demonstrate that MPQ-DM achieves significant accuracy gains under extremely low bit-widths compared with SOTA quantization methods. MPQ-DM achieves a 58\% FID decrease under W2A4 setting compared with baseline, while all other methods even collapse.

Yihua Shao, Yan Gu, Siyu Chen et al.

Large language models (LLMs) show impressive performance in solving complex language tasks. However, its large number of parameters presents significant challenges for the deployment. So, compressing LLMs to low bits can enable to deploy on resource-constrained devices. To address this problem, we propose gradient-aware weight quantization (GWQ), the first quantization approach for low-bit weight quantization that leverages gradients to localize outliers, requiring only a minimal amount of calibration data for outlier detection. GWQ retains the top 1\% outliers preferentially at FP16 precision, while the remaining non-outlier weights are stored in a low-bit. We widely evaluate GWQ on different task include language modeling, grounding detection, massive multitask language understanding and vision-language question and answering. Results show that models quantified by GWQ performs better than other quantization method. During quantization process, GWQ only need one calibration set to realize effective quant. Also, GWQ achieves 1.2x inference speedup in comparison to the original model and effectively reduces the inference memory.

Nicolas Baumann, Cheng Hu, Paviththiren Sivasothilingam et al.

Neural Networks (NNs) trained through supervised learning struggle with managing edge-case scenarios common in real-world driving due to the intractability of exhaustive datasets covering all edge-cases, making knowledge-driven approaches, akin to how humans intuitively detect unexpected driving behavior, a suitable complement to data-driven methods. This work proposes a hybrid architecture combining low-level Model Predictive Controller (MPC) with locally deployed Large Language Models (LLMs) to enhance decision-making and Human Machine Interaction (HMI). The DecisionxLLM module evaluates robotic state information against natural language instructions to ensure adherence to desired driving behavior. The MPCxLLM module then adjusts MPC parameters based on LLM-generated insights, achieving control adaptability while preserving the safety and constraint guarantees of traditional MPC systems. Further, to enable efficient on-board deployment and to eliminate dependency on cloud connectivity, we shift processing to the on-board computing platform: We propose an approach that exploits Retrieval Augmented Generation (RAG), Low Rank Adaptation (LoRA) fine-tuning, and quantization. Experimental results demonstrate that these enhancements yield significant improvements in reasoning accuracy by up to 10.45%, control adaptability by as much as 52.2%, and up to 10.5x increase in computational efficiency (tokens/s), validating the proposed framework's practicality for real-time deployment even on down-scaled robotic platforms. This work bridges high-level decision-making with low-level control adaptability, offering a synergistic framework for knowledge-driven and adaptive Autonomous Driving Systems (ADS).

Renshuai Tao, Manyi Le, Chuangchuang Tan et al.

Despite significant advances in deepfake detection, handling varying image quality, especially due to different compressions on online social networks (OSNs), remains challenging. Current methods succeed by leveraging correlations between paired images, whether raw or compressed. However, in open-world scenarios, paired data is scarce, with compressed images readily available but corresponding raw versions difficult to obtain. This imbalance, where unpaired data vastly outnumbers paired data, often leads to reduced detection performance, as existing methods struggle without corresponding raw images. To overcome this issue, we propose a novel approach named the open-world deepfake detection network (ODDN), which comprises two core modules: open-world data aggregation (ODA) and compression-discard gradient correction (CGC). ODA effectively aggregates correlations between compressed and raw samples through both fine-grained and coarse-grained analyses for paired and unpaired data, respectively. CGC incorporates a compression-discard gradient correction to further enhance performance across diverse compression methods in OSN. This technique optimizes the training gradient to ensure the model remains insensitive to compression variations. Extensive experiments conducted on 17 popular deepfake datasets demonstrate the superiority of the ODDN over SOTA baselines.

Haotong Qin, Xianglong Liu, Xudong Ma et al.

Deep neural networks for real-time video matting suffer significant computational limitations on edge devices, hindering their adoption in widespread applications such as online conferences and short-form video production. Binarization emerges as one of the most common compression approaches with compact 1-bit parameters and efficient bitwise operations. However, accuracy and efficiency limitations exist in the binarized video matting network due to its degenerated encoder and redundant decoder. Following a theoretical analysis based on the information bottleneck principle, the limitations are mainly caused by the degradation of prediction-relevant information in the intermediate features and the redundant computation in prediction-irrelevant areas. We present BiVM, an accurate and resource-efficient Binarized neural network for Video Matting. First, we present a series of binarized computation structures with elastic shortcuts and evolvable topologies, enabling the constructed encoder backbone to extract high-quality representation from input videos for accurate prediction. Second, we sparse the intermediate feature of the binarized decoder by masking homogeneous parts, allowing the decoder to focus on representation with diverse details while alleviating the computation burden for efficient inference. Furthermore, we construct a localized binarization-aware mimicking framework with the information-guided strategy, prompting matting-related representation in full-precision counterparts to be accurately and fully utilized. Comprehensive experiments show that the proposed BiVM surpasses alternative binarized video matting networks, including state-of-the-art (SOTA) binarization methods, by a substantial margin. Moreover, our BiVM achieves significant savings of 14.3x and 21.6x in computation and storage costs, respectively. We also evaluate BiVM on ARM CPU hardware.

Yujie Chen, Haotong Qin, Zhang Zhang et al.

State-Space Models (SSMs) have attracted considerable attention in Image Restoration (IR) due to their ability to scale linearly sequence length while effectively capturing long-distance dependencies. However, deploying SSMs to edge devices is challenging due to the constraints in memory, computing capacity, and power consumption, underscoring the need for efficient compression strategies. While low-bit quantization is an efficient model compression strategy for reducing size and accelerating IR tasks, SSM suffers substantial performance drops at ultra-low bit-widths (2-4 bits), primarily due to outliers that exacerbate quantization error. To address this challenge, we propose Q-MambaIR, an accurate, efficient, and flexible Quantized Mamba for IR tasks. Specifically, we introduce a Statistical Dynamic-balancing Learnable Scalar (DLS) to dynamically adjust the quantization mapping range, thereby mitigating the peak truncation loss caused by extreme values. Furthermore, we design a Range-floating Flexible Allocator (RFA) with an adaptive threshold to flexibly round values. This approach preserves high-frequency details and maintains the SSM's feature extraction capability. Notably, RFA also enables pre-deployment weight quantization, striking a balance between computational efficiency and model accuracy. Extensive experiments on IR tasks demonstrate that Q-MambaIR consistently outperforms existing quantized SSMs, achieving much higher state-of-the-art (SOTA) accuracy results with only a negligible increase in training computation and storage saving.

Weilun Feng, Chuanguang Yang, Haotong Qin et al.

Diffusion models have demonstrated remarkable performance on vision generation tasks. However, the high computational complexity hinders its wide application on edge devices. Quantization has emerged as a promising technique for inference acceleration and memory reduction. However, existing quantization methods do not generalize well under extremely low-bit (2-4 bit) quantization. Directly applying these methods will cause severe performance degradation. We identify that the existing quantization framework suffers from the outlier-unfriendly quantizer design, suboptimal initialization, and optimization strategy. We present MPQ-DMv2, an improved \textbf{M}ixed \textbf{P}recision \textbf{Q}uantization framework for extremely low-bit \textbf{D}iffusion \textbf{M}odels. For the quantization perspective, the imbalanced distribution caused by salient outliers is quantization-unfriendly for uniform quantizer. We propose \textit{Flexible Z-Order Residual Mixed Quantization} that utilizes an efficient binary residual branch for flexible quant steps to handle salient error. For the optimization framework, we theoretically analyzed the convergence and optimality of the LoRA module and propose \textit{Object-Oriented Low-Rank Initialization} to use prior quantization error for informative initialization. We then propose \textit{Memory-based Temporal Relation Distillation} to construct an online time-aware pixel queue for long-term denoising temporal information distillation, which ensures the overall temporal consistency between quantized and full-precision model. Comprehensive experiments on various generation tasks show that our MPQ-DMv2 surpasses current SOTA methods by a great margin on different architectures, especially under extremely low-bit widths.

Nicola Farronato, Florian Scheidegger, Mattia Rigotti et al. · ibm-research

The Segment Anything Model 2 (SAM2) has gained significant attention as a foundational approach for promptable image and video segmentation. However, its expensive computational and memory consumption poses a severe challenge for its application in resource-constrained scenarios. In this paper, we propose an accurate low-bit quantization method for efficient SAM2, termed Q-SAM2. To address the performance degradation caused by the singularities in weight and activation distributions during quantization, Q-SAM2 introduces two novel technical contributions. We first introduce a linear layer calibration method for low-bit initialization of SAM2, which minimizes the Frobenius norm over a small image batch to reposition weight distributions for improved quantization. We then propose a Quantization-Aware Training (QAT) pipeline that applies clipping to suppress outliers and allows the network to adapt to quantization thresholds during training. Our comprehensive experiments demonstrate that Q-SAM2 allows for highly accurate inference while substantially improving efficiency. Both quantitative and visual results show that our Q-SAM2 surpasses existing state-of-the-art general quantization schemes, especially for ultra-low 2-bit quantization. While designed for quantization-aware training, our proposed calibration technique also proves effective in post-training quantization, achieving up to a 66% mIoU accuracy improvement over non-calibrated models.

Haotong Qin, Cheng Hu, Michele Magno

Large Language Model (LLM)-based Vision-Language Models (VLMs) have substantially extended the boundaries of visual understanding capabilities. However, their high computational demands hinder deployment on resource-constrained edge devices. A key source of inefficiency stems from the VLM's need to process dense and redundant visual information. Visual inputs contain significant regions irrelevant to text semantics, rendering the associated computations ineffective for inference. This paper introduces a novel Event-Priori-Based Vision-Language Model, termed EP-VLM. Its core contribution is a novel mechanism leveraging motion priors derived from dynamic event vision to enhance VLM efficiency. Inspired by human visual cognition, EP-VLM first employs event data to guide the patch-wise sparsification of RGB visual inputs, progressively concentrating VLM computation on salient regions of the visual input. Subsequently, we construct a position-preserving tokenization strategy for the visual encoder within the VLM architecture. This strategy processes the event-guided, unstructured, sparse visual input while accurately preserving positional understanding within the visual input. Experimental results demonstrate that EP-VLM achieves significant efficiency improvements while maintaining nearly lossless accuracy compared to baseline models from the Qwen2-VL series. For instance, against the original Qwen2-VL-2B, EP-VLM achieves 50% FLOPs savings while retaining 98% of the original accuracy on the RealWorldQA dataset. This work demonstrates the potential of event-based vision priors for improving VLM inference efficiency, paving the way for creating more efficient and deployable VLMs for sustainable visual understanding at the edge.

Pietro Bonazzi, Christian Vogt, Michael Jost et al.

Ensuring robust and real-time obstacle avoidance is critical for the safe operation of autonomous robots in dynamic, real-world environments. This paper proposes a neural network framework for predicting the time and collision position of an unmanned aerial vehicle with a dynamic object, using RGB and event-based vision sensors. The proposed architecture consists of two separate encoder branches, one for each modality, followed by fusion by self-attention to improve prediction accuracy. To facilitate benchmarking, we leverage the ABCD [8] dataset collected that enables detailed comparisons of single-modality and fusion-based approaches. At the same prediction throughput of 50Hz, the experimental results show that the fusion-based model offers an improvement in prediction accuracy over single-modality approaches of 1% on average and 10% for distances beyond 0.5m, but comes at the cost of +71% in memory and + 105% in FLOPs. Notably, the event-based model outperforms the RGB model by 4% for position and 26% for time error at a similar computational cost, making it a competitive alternative. Additionally, we evaluate quantized versions of the event-based models, applying 1- to 8-bit quantization to assess the trade-offs between predictive performance and computational efficiency. These findings highlight the trade-offs of multi-modal perception using RGB and event-based cameras in robotic applications.

Yi Guo, Yiqian He, Xiaoyang Li et al.

Knowledge Distillation (KD) emerges as one of the most promising compression technologies to run advanced deep neural networks on resource-limited devices. In order to train a small network (student) under the guidance of a large network (teacher), the intuitive method is regularizing the feature maps or logits of the student using the teacher's information. However, existing methods either over-restrict the student to learn all information from the teacher, which lead to some bad local minimum, or use various fancy and elaborate modules to process and align features, which are complex and lack generality. In this work, we proposed an abstract and general paradigm for the KD task, referred to as DIMensionality Reduction KD (RdimKD), which solely relies on dimensionality reduction, with a very minor modification to naive L2 loss. RdimKD straightforwardly utilizes a projection matrix to project both the teacher's and student's feature maps onto a low-dimensional subspace, which are then optimized during training. RdimKD achieves the goal in the simplest way that not only does the student get valuable information from the teacher, but it also ensures sufficient flexibility to adapt to the student's low-capacity reality. Our extensive empirical findings indicate the effectiveness of RdimKD across various learning tasks and diverse network architectures.

Xingyu Zheng, Haotong Qin, Yuye Li et al.

Post-training quantization (PTQ) offers an efficient approach to compressing large language models (LLMs), significantly reducing memory access and computational costs. Existing compensation-based weight calibration methods often rely on a second-order Taylor expansion to model quantization error, under the assumption that the first-order term is negligible in well-trained full-precision models. However, we reveal that the progressive compensation process introduces accumulated first-order deviations between latent weights and their full-precision counterparts, making this assumption fundamentally flawed. To address this, we propose FOEM, a novel PTQ method that explicitly incorporates first-order gradient terms to improve quantization error compensation. FOEM approximates gradients by performing a first-order Taylor expansion around the pre-quantization weights. This yields an approximation based on the difference between latent and full-precision weights as well as the Hessian matrix. When substituted into the theoretical solution, the formulation eliminates the need to explicitly compute the Hessian, thereby avoiding the high computational cost and limited generalization of backpropagation-based gradient methods. This design introduces only minimal additional computational overhead. Extensive experiments across a wide range of models and benchmarks demonstrate that FOEM consistently outperforms the classical GPTQ method. In 3-bit weight-only quantization, FOEM reduces the perplexity of Llama3-8B by 17.3% and increases the 5-shot MMLU accuracy from 53.8% achieved by GPTAQ to 56.1%. Moreover, FOEM can be seamlessly combined with advanced techniques such as SpinQuant, delivering additional gains under the challenging W4A4KV4 setting and further narrowing the performance gap with full-precision baselines, surpassing existing state-of-the-art methods.

Tianrui Zhu, Houyuan Chen, Ruihao Gong et al.

Video matting is crucial for applications such as film production and virtual reality, yet deploying its computationally intensive models on resource-constrained devices presents challenges. Quantization is a key technique for model compression and acceleration. As an efficient approach, Post-Training Quantization (PTQ) is still in its nascent stages for video matting, facing significant hurdles in maintaining accuracy and temporal coherence. To address these challenges, this paper proposes a novel and general PTQ framework specifically designed for video matting models, marking, to the best of our knowledge, the first systematic attempt in this domain. Our contributions include: (1) A two-stage PTQ strategy that combines block-reconstruction-based optimization for fast, stable initial quantization and local dependency capture, followed by a global calibration of quantization parameters to minimize accuracy loss. (2) A Statistically-Driven Global Affine Calibration (GAC) method that enables the network to compensate for cumulative statistical distortions arising from factors such as neglected BN layer effects, even reducing the error of existing PTQ methods on video matting tasks up to 20%. (3) An Optical Flow Assistance (OFA) component that leverages temporal and semantic priors from frames to guide the PTQ process, enhancing the model's ability to distinguish moving foregrounds in complex scenes and ultimately achieving near full-precision performance even under ultra-low-bit quantization. Comprehensive quantitative and visual results show that our PTQ4VM achieves the state-of-the-art accuracy performance across different bit-widths compared to the existing quantization methods. We highlight that the 4-bit PTQ4VM even achieves performance close to the full-precision counterpart while enjoying 8x FLOP savings.

Jin Hu, Xianglong Liu, Jiakai Wang et al.

Physical adversarial examples (PAEs) are regarded as whistle-blowers of real-world risks in deep-learning applications, thus worth further investigation. However, current PAE generation studies show limited adaptive attacking ability to diverse and varying scenes, revealing the urgent requirement of dynamic PAEs that are generated in real time and conditioned on the observation from the attacker. The key challenge in generating dynamic PAEs is learning the sparse relation between PAEs and the observation of attackers under the noisy feedback of attack training. To address the challenge, we present DynamicPAE, the first generative framework that enables scene-aware real-time physical attacks. Specifically, to address the noisy feedback problem that obfuscates the exploration of scene-related PAEs, we introduce the residual-guided adversarial pattern exploration technique. Residual-guided training, which relaxes the attack training with a reconstruction task, is proposed to enrich the feedback information, thereby achieving a more comprehensive exploration of PAEs. To address the alignment problem between the trained generator and the real-world scenario, we introduce the distribution-matched attack scenario alignment, consisting of the conditional-uncertainty-aligned data module and the skewness-aligned objective re-weighting module. The former aligns the training environment with the incomplete observation of the real-world attacker. The latter facilitates consistent stealth control across different attack targets with the skewness controller. Extensive digital and physical evaluations demonstrate the superior attack performance of DynamicPAE, attaining a 2.07 $\times$ boost (58.8% average AP drop under attack) on representative object detectors (e.g., DETR) over state-of-the-art static PAE generating methods. Overall, our work opens the door to end-to-end modeling of dynamic PAEs.

Rui Yin, Haotong Qin, Yulun Zhang et al.

Dense prediction is a critical task in computer vision. However, previous methods often require extensive computational resources, which hinders their real-world application. In this paper, we propose BiDense, a generalized binary neural network (BNN) designed for efficient and accurate dense prediction tasks. BiDense incorporates two key techniques: the Distribution-adaptive Binarizer (DAB) and the Channel-adaptive Full-precision Bypass (CFB). The DAB adaptively calculates thresholds and scaling factors for binarization, effectively retaining more information within BNNs. Meanwhile, the CFB facilitates full-precision bypassing for binary convolutional layers undergoing various channel size transformations, which enhances the propagation of real-valued signals and minimizes information loss. By leveraging these techniques, BiDense preserves more real-valued information, enabling more accurate and detailed dense predictions in BNNs. Extensive experiments demonstrate that our framework achieves performance levels comparable to full-precision models while significantly reducing memory usage and computational costs.