Zhiteng Li

Leyang Chen, Junyi Wu, Zhiteng Li et al.

Streaming 3D reconstruction from long monocular video sequences requires maintaining a key-value (KV) cache that grows linearly with sequence length, creating a severe memory bottleneck. Existing approaches either truncate the cache to a fixed set of anchor frames, leading to reconstruction quality degradation, or rely on attention-score heuristics that are agnostic to 3D scene structure, failing to preserve geometrically valuable tokens. To address these problems, we present GHOST (Geometry-Hierarchical Online Streaming Token Eviction), a training-free KV cache management framework that exploits the model's own 3D geometry outputs to evict redundant tokens online. GHOST introduces three mutually reinforcing innovations: a hierarchical dual-level importance scoring scheme, a privilege mechanism that protects special tokens from eviction, and a cosine-similarity-guided layer-wise budget allocation. Experiments on various benchmarks show that GHOST preserves excellent reconstruction quality while cutting the KV cache by nearly half and delivering 1.75x faster inference compared to state-of-the-art methods. Our code is available at https://github.com/lokiniuniu/GHOST.

Xianglong Yan, ChengZhu Bao, Zhiteng Li et al.

Large language models (LLMs) deliver strong performance, but their high compute and memory costs make deployment difficult in resource-constrained scenarios. Weight-only post-training quantization (PTQ) is appealing, as it reduces memory usage and enables practical speedup without low-bit operators or specialized hardware. However, accuracy often degrades significantly in weight-only PTQ at sub-4-bit precision, and our analysis identifies two main causes: (1) down-projection matrices are a well-known quantization bottleneck, but maintaining their fidelity often requires extra bit-width; (2) weight quantization induces activation deviations, but effective correction strategies remain underexplored. To address these issues, we propose D$^2$Quant, a novel weight-only PTQ framework that improves quantization from both the weight and activation perspectives. On the weight side, we design a Dual-Scale Quantizer (DSQ) tailored to down-projection matrices, with an absorbable scaling factor that significantly improves accuracy without increasing the bit budget. On the activation side, we propose Deviation-Aware Correction (DAC), which incorporates a mean-shift correction within LayerNorm to mitigate quantization-induced activation distribution shifts. Extensive experiments across multiple LLM families and evaluation metrics show that D$^2$Quant delivers superior performance for weight-only PTQ at sub-4-bit precision. The code and models will be available at https://github.com/XIANGLONGYAN/D2Quant.

Chengzhu Bao, Xianglong Yan, Zhiteng Li et al.

NVFP4 has recently emerged as an efficient 4-bit microscaling format for large language models (LLMs), offering superior numerical fidelity with native hardware support. However, existing methods often yield suboptimal performance due to inflexible scale selection and the coupled treatment of quantization and dequantization scales. To address these issues, we propose Scale Optimization for Accurate Reconstruction (SOAR), a novel post-training quantization framework that improves the accuracy of NVFP4 quantization. At its core, SOAR features Closed-form Joint Scale Optimization (CJSO), which jointly optimizes global and block-wise scales via analytical solutions derived from reconstruction error minimization. Furthermore, it incorporates Decoupled Scale Search (DSS). DSS decouples the high-precision quantization scale from its constrained dequantization counterpart, and performs discrete search to mitigate precision loss from scale quantization. Extensive experiments across multiple LLMs show that our method consistently outperforms existing NVFP4 quantization baselines, achieving superior accuracy under the same memory footprint with no additional hardware overhead. The code and models will be available at https://github.com/steven-bao1/SOAR.

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.

Zhiteng Li, Mingyuan Xia, Jingyuan Zhang et al.

Large language models (LLMs) have achieved remarkable success in natural language processing (NLP) tasks, yet their substantial memory requirements present significant challenges for deployment on resource-constrained devices. Singular Value Decomposition (SVD) has emerged as a promising compression technique for LLMs, offering considerable reductions in memory overhead. However, existing SVD-based methods often struggle to effectively mitigate the errors introduced by SVD truncation, leading to a noticeable performance gap when compared to the original models. Furthermore, applying a uniform compression ratio across all transformer layers fails to account for the varying importance of different layers. To address these challenges, we propose AdaSVD, an adaptive SVD-based LLM compression approach. Specifically, AdaSVD introduces adaComp, which adaptively compensates for SVD truncation errors by alternately updating the singular matrices $\mathcal{U}$ and $\mathcal{V}^\top$. Additionally, AdaSVD introduces adaCR, which adaptively assigns layer-specific compression ratios based on the relative importance of each layer. Extensive experiments across multiple LLM/VLM families and evaluation metrics demonstrate that AdaSVD consistently outperforms state-of-the-art (SOTA) SVD-based methods, achieving superior performance with significantly reduced memory requirements. Code and models of AdaSVD will be available at https://github.com/ZHITENGLI/AdaSVD.

Junyi Wu, Zhiteng Li, Zheng Hui et al.

Recently, Diffusion Transformers (DiTs) have emerged as a dominant architecture in video generation, surpassing U-Net-based models in terms of performance. However, the enhanced capabilities of DiTs come with significant drawbacks, including increased computational and memory costs, which hinder their deployment on resource-constrained devices. Current acceleration techniques, such as quantization and cache mechanism, offer limited speedup and are often applied in isolation, failing to fully address the complexities of DiT architectures. In this paper, we propose QuantCache, a novel training-free inference acceleration framework that jointly optimizes hierarchical latent caching, adaptive importance-guided quantization, and structural redundancy-aware pruning. QuantCache achieves an end-to-end latency speedup of 6.72$\times$ on Open-Sora with minimal loss in generation quality. Extensive experiments across multiple video generation benchmarks demonstrate the effectiveness of our method, setting a new standard for efficient DiT inference. The code and models will be available at https://github.com/JunyiWuCode/QuantCache.

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, Tianao Zhang, Zhiteng Li et al.

Large language models (LLMs) have achieved remarkable progress in natural language processing, but their high computational and memory costs hinder deployment on resource-constrained devices. Binarization represents the most extreme form of quantization, yet binarized models still contain redundancy that can be further removed. Pruning provides a natural way to eliminate such redundancy, but naïve combination with binarization often results in severe performance degradation. In this paper, we propose Progressive Binarization with Semi-Structured Pruning (PBS$^2$P), a novel post-training framework that seamlessly integrates binarization and semi-structured pruning. We first propose Stepwise semi-structured Pruning with Binarization Optimization (SPBO), which progressively introduces sparsity while optimizing binarization parameters to jointly reduce pruning and quantization error, yielding more stable and accurate compression. Additionally, we propose a Coarse-to-Fine Search (CFS) that first allocates pruning ratios and then refines element selection, further enhancing overall performance. Extensive experiments across multiple LLM families show that PBS$^2$P consistently outperforms state-of-the-art (SOTA) binary post-training quantization methods in both perplexity and downstream accuracy. The code and models will be available at https://github.com/XIANGLONGYAN/PBS2P.

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.

Zhiteng Li, Hanxuan Li, Junyi Wu et al.

Diffusion Transformers (DiTs) have emerged as the state-of-the-art architecture for video generation, yet their computational and memory demands hinder practical deployment. While post-training quantization (PTQ) presents a promising approach to accelerate Video DiT models, existing methods suffer from two critical limitations: (1) dependence on computation-heavy and inflexible calibration procedures, and (2) considerable performance deterioration after quantization. To address these challenges, we propose DVD-Quant, a novel Data-free quantization framework for Video DiTs. Our approach integrates three key innovations: (1) Bounded-init Grid Refinement (BGR) and (2) Auto-scaling Rotated Quantization (ARQ) for calibration data-free quantization error reduction, as well as (3) $δ$-Guided Bit Switching ($δ$-GBS) for adaptive bit-width allocation. Extensive experiments across multiple video generation benchmarks demonstrate that DVD-Quant achieves an approximately 2$\times$ speedup over full-precision baselines on advanced DiT models while maintaining visual fidelity. Notably, DVD-Quant is the first to enable W4A4 PTQ for Video DiTs without compromising video quality. Code and models will be available at https://github.com/lhxcs/DVD-Quant.

Guangshuo Qin, Zhiteng Li, Zheng Chen et al.

Mixture-of-Experts(MoE) Vision-Language Models (VLMs) offer remarkable performance but incur prohibitive memory and computational costs, making compression essential. Post-Training Quantization (PTQ) is an effective training-free technique to address the massive memory and computation overhead. Existing quantization paradigms fall short as they are oblivious to two critical forms of heterogeneity: the inherent discrepancy between vision and language tokens, and the non-uniform contribution of different experts. To bridge this gap, we propose Visual Expert Quantization (VEQ), a dual-aware quantization framework designed to simultaneously accommodate cross-modal differences and heterogeneity between experts. Specifically, VEQ incorporates 1)Modality-expert-aware Quantization, which utilizes expert activation frequency to prioritize error minimization for pivotal experts, and 2)Modality-affinity-aware Quantization, which constructs an enhanced Hessian matrix by integrating token-expert affinity with modality information to guide the calibration process. Extensive experiments across diverse benchmarks verify that VEQ consistently outperforms state-of-the-art baselines. Specifically, under the W3A16 configuration, our method achieves significant average accuracy gains of 2.04\% on Kimi-VL and 3.09\% on Qwen3-VL compared to the previous SOTA quantization methods, demonstrating superior robustness across various multimodal tasks. Our code will be available at https://github.com/guangshuoqin/VEQ.

Kai Liu, Dehui Wang, Zhiteng Li et al.

Low-bit model quantization for image super-resolution (SR) is a longstanding task that is renowned for its surprising compression and acceleration ability. However, accuracy degradation is inevitable when compressing the full-precision (FP) model to ultra-low bit widths (2~4 bits). Experimentally, we observe that the degradation of quantization is mainly attributed to the quantization of activation instead of model weights. In numerical analysis, the condition number of weights could measure how much the output value can change for a small change in the input argument, inherently reflecting the quantization error. Therefore, we propose CondiQuant, a condition number based low-bit post-training quantization for image super-resolution. Specifically, we formulate the quantization error as the condition number of weight metrics. By decoupling the representation ability and the quantization sensitivity, we design an efficient proximal gradient descent algorithm to iteratively minimize the condition number and maintain the output still. With comprehensive experiments, we demonstrate that CondiQuant outperforms existing state-of-the-art post-training quantization methods in accuracy without computation overhead and gains the theoretically optimal compression ratio in model parameters. Our code and model are released at https://github.com/Kai-Liu001/CondiQuant.

Yixin Tang, Jiawei Guo, Junxian Li et al.

Recently, diffusion-based object removal models have achieved impressive results in eliminating objects and their associated visual effects. However, they indiscriminately denoise all tokens across all timesteps, ignoring that removal usually involves small foreground regions. This strategy introduces substantial computational overhead and prolonged inference times. To overcome this computational burden, we propose a latent discriminator to implement Region-aware Adversarial Distillation (RAD), yielding a highly efficient few-step model named FlashClear. Furthermore, tailored to few-step diffusion models, we propose FPAC (Foreground-Prioritized Asymmetric Attention and Caching), a training-free acceleration strategy. Extensive experiments demonstrate that our framework provides massive acceleration while maintaining or exceeding the performance of our base model, ObjectClear. Notably, on the OBER benchmark, our FlashClear achieves up to 8.26$\times$ and 122$\times$ speedup over ObjectClear and OmniPaint, respectively, while maintaining high visual quality and fidelity.

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.

Junyi Wu, Zhiteng Li, Haotong Qin et al.

Text-guided image editing with diffusion models has achieved remarkable quality but suffers from prohibitive latency, hindering real-world applications. We introduce FlashEdit, a novel framework designed to enable high-fidelity, real-time image editing. Its efficiency stems from three key innovations: (1) a One-Step Inversion-and-Editing (OSIE) pipeline that bypasses costly iterative processes; (2) a Background Shield (BG-Shield) technique that guarantees background preservation by selectively modifying features only within the edit region; and (3) a Sparsified Spatial Cross-Attention (SSCA) mechanism that ensures precise, localized edits by suppressing semantic leakage to the background. Extensive experiments demonstrate that FlashEdit maintains superior background consistency and structural integrity, while performing edits in under 0.2 seconds, which is an over 150$\times$ speedup compared to prior multi-step methods. Our code will be made publicly available at https://github.com/JunyiWuCode/FlashEdit.

Kai Liu, Kaicheng Yang, Zheng Chen et al.

While super-resolution (SR) methods based on diffusion models (DM) have demonstrated inspiring performance, their deployment is impeded due to the heavy request of memory and computation. Recent researchers apply two kinds of methods to compress or fasten the DM. One is to compress the DM into 1-bit, aka binarization, alleviating the storage and computation pressure. The other distills the multi-step DM into only one step, significantly speeding up inference process. Nonetheless, it remains impossible to deploy DM to resource-limited edge devices. To address this problem, we propose BiMaCoSR, which combines binarization and one-step distillation to obtain extreme compression and acceleration. To prevent the catastrophic collapse of the model caused by binarization, we proposed sparse matrix branch (SMB) and low rank matrix branch (LRMB). Both auxiliary branches pass the full-precision (FP) information but in different ways. SMB absorbs the extreme values and its output is high rank, carrying abundant FP information. Whereas, the design of LRMB is inspired by LoRA and is initialized with the top r SVD components, outputting low rank representation. The computation and storage overhead of our proposed branches can be safely ignored. Comprehensive comparison experiments are conducted to exhibit BiMaCoSR outperforms current state-of-the-art binarization methods and gains competitive performance compared with FP one-step model. BiMaCoSR achieves a 23.8x compression ratio and a 27.4x speedup ratio compared to FP counterpart. Our code and model are available at https://github.com/Kai-Liu001/BiMaCoSR.