Yang Zhao

Qiang Huang, Jiawei Jiang, Xi Susie Rao et al. · eth-zurich

To handle graphs in which features or connectivities are evolving over time, a series of temporal graph neural networks (TGNNs) have been proposed. Despite the success of these TGNNs, the previous TGNN evaluations reveal several limitations regarding four critical issues: 1) inconsistent datasets, 2) inconsistent evaluation pipelines, 3) lacking workload diversity, and 4) lacking efficient comparison. Overall, there lacks an empirical study that puts TGNN models onto the same ground and compares them comprehensively. To this end, we propose BenchTemp, a general benchmark for evaluating TGNN models on various workloads. BenchTemp provides a set of benchmark datasets so that different TGNN models can be fairly compared. Further, BenchTemp engineers a standard pipeline that unifies the TGNN evaluation. With BenchTemp, we extensively compare the representative TGNN models on different tasks (e.g., link prediction and node classification) and settings (transductive and inductive), w.r.t. both effectiveness and efficiency metrics. We have made BenchTemp publicly available at https://github.com/qianghuangwhu/benchtemp.

Junlin Long, Zeyu Zhang, Xu Deng et al.

Embodied visual navigation, where an agent perceives a complex environment and acts to reach a goal from raw sensory input, underpins a wide range of applications such as household service robotics, assistive robotics, and large-scale autonomous exploration. However, recent attempts to unify vision-and-language navigation (VLN) and object goal navigation (ObjNav) remain at the level of architectural fusion, mixed-task training, and large vision-language pretraining, without examining whether independently trained vision and language encoders may already share a common semantic structure. Moreover, even object-centric topological maps still ground language goals through explicit cross-modal supervision such as CLIP or large vision-language models, leaving open whether such grounding is possible from a purely vision-built map. To address these challenges, we extend the Platonic Representation Hypothesis to embodied navigation and recast vision-only ObjNav, cross-modal ObjNav, and VLN as three different interfaces to the same object-centric semantic manifold. We further introduce PlatonicNav, a training-free framework whose Platonic Topological Map fuses geometric and semantic node distances from a self-supervised visual encoder, and grounds language goals via blind matching without any paired vision-language data. Extensive experiments on simulation benchmarks including HM3D-IIN, OVON, and R2R-CE on MP3D, together with deployment on Unitree Go2, demonstrate that PlatonicNav generalizes across tasks, modalities, and embodiments without explicit cross-modal training. Code: https://github.com/AIGeeksGroup/PlatonicNav. Website: https://aigeeksgroup.github.io/PlatonicNav.

Xiaopei Wu, Yang Zhao, Liang Peng et al.

Current 3D object detection methods heavily rely on an enormous amount of annotations. Semi-supervised learning can be used to alleviate this issue. Previous semi-supervised 3D object detection methods directly follow the practice of fully-supervised methods to augment labeled and unlabeled data, which is sub-optimal. In this paper, we design a data augmentation method for semi-supervised learning, which we call Semi-Sampling. Specifically, we use ground truth labels and pseudo labels to crop gt samples and pseudo samples on labeled frames and unlabeled frames, respectively. Then we can generate a gt sample database and a pseudo sample database. When training a teacher-student semi-supervised framework, we randomly select gt samples and pseudo samples to both labeled frames and unlabeled frames, making a strong data augmentation for them. Our semi-sampling can be regarded as an extension of gt-sampling to semi-supervised learning. Our method is simple but effective. We consistently improve state-of-the-art methods on ScanNet, SUN-RGBD, and KITTI benchmarks by large margins. For example, when training using only 10% labeled data on ScanNet, we achieve 3.1 mAP and 6.4 mAP improvement upon 3DIoUMatch in terms of mAP@0.25 and mAP@0.5. When training using only 1% labeled data on KITTI, we boost 3DIoUMatch by 3.5 mAP, 6.7 mAP and 14.1 mAP on car, pedestrian and cyclist classes. Codes will be made publicly available at https://github.com/LittlePey/Semi-Sampling.

Mingxuan Lu, Zhichao Han, Susie Xi Rao et al. · eth-zurich

Detecting fraudulent transactions is an essential component to control risk in e-commerce marketplaces. Apart from rule-based and machine learning filters that are already deployed in production, we want to enable efficient real-time inference with graph neural networks (GNNs), which is useful to catch multihop risk propagation in a transaction graph. However, two challenges arise in the implementation of GNNs in production. First, future information in a dynamic graph should not be considered in message passing to predict the past. Second, the latency of graph query and GNN model inference is usually up to hundreds of milliseconds, which is costly for some critical online services. To tackle these challenges, we propose a Batch and Real-time Inception GrapH Topology (BRIGHT) framework to conduct an end-to-end GNN learning that allows efficient online real-time inference. BRIGHT framework consists of a graph transformation module (Two-Stage Directed Graph) and a corresponding GNN architecture (Lambda Neural Network). The Two-Stage Directed Graph guarantees that the information passed through neighbors is only from the historical payment transactions. It consists of two subgraphs representing historical relationships and real-time links, respectively. The Lambda Neural Network decouples inference into two stages: batch inference of entity embeddings and real-time inference of transaction prediction. Our experiments show that BRIGHT outperforms the baseline models by >2\% in average w.r.t.~precision. Furthermore, BRIGHT is computationally efficient for real-time fraud detection. Regarding end-to-end performance (including neighbor query and inference), BRIGHT can reduce the P99 latency by >75\%. For the inference stage, our speedup is on average 7.8$\times$ compared to the traditional GNN.

PSBC LLM Team, Huawei LLM Team, Ruihan Long et al.

Large language models (LLMs) drive significant financial innovations, yet their high-concurrency deployment is severely bottlenecked by KV cache memory overhead, which inflates infrastructure costs and throttles scalability. To address this, we propose YouZhi-LLM, a highly efficient financial LLM empowered by a comprehensive structural transition and training pipeline natively built on the Huawei Ascend ecosystem. At its algorithmic core, YouZhi-LLM features a layer-adaptive GQA-to-MLA transition framework that dynamically assigns per-layer FreqFold sizes, maximizing KV-cache compression while minimizing perplexity degradation. To recover representation capacity and inject domain expertise, the Ascend-based training pipeline seamlessly integrates generalized knowledge distillation with financial-specific supervised fine-tuning. Evaluations demonstrate the superiority of this systematic approach, with the adaptive transition reducing perplexity degradation by up to 35% over uniform baselines. Crucially, when evaluated on Ascend NPUs via vLLM-Ascend, the massive KV-cache reduction translates directly into deployment efficiency. Compared to their respective base models, YouZhi-7B yields a 12.3% improvement in average financial benchmark score alongside a 2.69$\times$ increase in maximum concurrency; similarly, YouZhi-14B achieves a 7.0% accuracy gain and a 2.43$\times$ concurrency boost, establishing a new paradigm for cost-effective, high-throughput financial inference.

Yang Zhao, Di Huang, Chongxiao Li et al.

The design flow of processors, particularly in hardware description languages (HDL) like Verilog and Chisel, is complex and costly. While recent advances in large language models (LLMs) have significantly improved coding tasks in software languages such as Python, their application in HDL generation remains limited due to the scarcity of high-quality HDL data. Traditional methods of adapting LLMs for hardware design rely on synthetic HDL datasets, which often suffer from low quality because even advanced LLMs like GPT perform poorly in the HDL domain. Moreover, these methods focus solely on chat tasks and the Verilog language, limiting their application scenarios. In this paper, we observe that: (1) HDL code collected from the real world is of higher quality than code generated by LLMs. (2) LLMs like GPT-3.5 excel in summarizing HDL code rather than generating it. (3) An explicit language tag can help LLMs better adapt to the target language when there is insufficient data. Based on these observations, we propose an efficient LLM fine-tuning pipeline for HDL generation that integrates a multi-level summarization data synthesis process with a novel Chat-FIM-Tag supervised fine-tuning method. The pipeline enhances the generation of HDL code from natural language descriptions and enables the handling of various tasks such as chat and infilling incomplete code. Utilizing this pipeline, we introduce CodeV, a series of HDL generation LLMs. Among them, CodeV-All not only possesses a more diverse range of language abilities, i.e. Verilog and Chisel, and a broader scope of tasks, i.e. Chat and fill-in-middle (FIM), but it also achieves performance on VerilogEval that is comparable to or even surpasses that of CodeV-Verilog fine-tuned on Verilog only, making them the first series of open-source LLMs designed for multi-scenario HDL generation.

Huihong Shi, Haoran You, Yang Zhao et al.

Multiplication is arguably the most cost-dominant operation in modern deep neural networks (DNNs), limiting their achievable efficiency and thus more extensive deployment in resource-constrained applications. To tackle this limitation, pioneering works have developed handcrafted multiplication-free DNNs, which require expert knowledge and time-consuming manual iteration, calling for fast development tools. To this end, we propose a Neural Architecture Search and Acceleration framework dubbed NASA, which enables automated multiplication-reduced DNN development and integrates a dedicated multiplication-reduced accelerator for boosting DNNs' achievable efficiency. Specifically, NASA adopts neural architecture search (NAS) spaces that augment the state-of-the-art one with hardware-inspired multiplication-free operators, such as shift and adder, armed with a novel progressive pretrain strategy (PGP) together with customized training recipes to automatically search for optimal multiplication-reduced DNNs; On top of that, NASA further develops a dedicated accelerator, which advocates a chunk-based template and auto-mapper dedicated for NASA-NAS resulting DNNs to better leverage their algorithmic properties for boosting hardware efficiency. Experimental results and ablation studies consistently validate the advantages of NASA's algorithm-hardware co-design framework in terms of achievable accuracy and efficiency tradeoffs. Codes are available at https://github.com/GATECH-EIC/NASA.

Guohui Cai, Ruicheng Zhang, Hongyang He et al.

Pulmonary nodules are critical indicators for the early diagnosis of lung cancer, making their detection essential for timely treatment. However, traditional CT imaging methods suffered from cumbersome procedures, low detection rates, and poor localization accuracy. The subtle differences between pulmonary nodules and surrounding tissues in complex lung CT images, combined with repeated downsampling in feature extraction networks, often lead to missed or false detections of small nodules. Existing methods such as FPN, with its fixed feature fusion and limited receptive field, struggle to effectively overcome these issues. To address these challenges, our paper proposed three key contributions: Firstly, we proposed MSDet, a multiscale attention and receptive field network for detecting tiny pulmonary nodules. Secondly, we proposed the extended receptive domain (ERD) strategy to capture richer contextual information and reduce false positives caused by nodule occlusion. We also proposed the position channel attention mechanism (PCAM) to optimize feature learning and reduce multiscale detection errors, and designed the tiny object detection block (TODB) to enhance the detection of tiny nodules. Lastly, we conducted thorough experiments on the public LUNA16 dataset, achieving state-of-the-art performance, with an mAP improvement of 8.8% over the previous state-of-the-art method YOLOv8. These advancements significantly boosted detection accuracy and reliability, providing a more effective solution for early lung cancer diagnosis. The code will be available at https://github.com/CaiGuoHui123/MSDet

Lei Shen, Jianlong Jin, Ruixin Zhang et al. · tencent-ai

Palmprint recently shows great potential in recognition applications as it is a privacy-friendly and stable biometric. However, the lack of large-scale public palmprint datasets limits further research and development of palmprint recognition. In this paper, we propose a novel realistic pseudo-palmprint generation (RPG) model to synthesize palmprints with massive identities. We first introduce a conditional modulation generator to improve the intra-class diversity. Then an identity-aware loss is proposed to ensure identity consistency against unpaired training. We further improve the Bézier palm creases generation strategy to guarantee identity independence. Extensive experimental results demonstrate that synthetic pretraining significantly boosts the recognition model performance. For example, our model improves the state-of-the-art BézierPalm by more than $5\%$ and $14\%$ in terms of TAR@FAR=1e-6 under the $1:1$ and $1:3$ Open-set protocol. When accessing only $10\%$ of the real training data, our method still outperforms ArcFace with $100\%$ real training data, indicating that we are closer to real-data-free palmprint recognition.

Shengbo Tan, Zeyu Zhang, Ying Cai et al.

Medical imaging segmentation plays a significant role in the automatic recognition and analysis of lesions. State-of-the-art methods, particularly those utilizing transformers, have been prominently adopted in 3D semantic segmentation due to their superior performance in scalability and generalizability. However, plain vision transformers encounter challenges due to their neglect of local features and their high computational complexity. To address these challenges, we introduce three key contributions: Firstly, we proposed SegStitch, an innovative architecture that integrates transformers with denoising ODE blocks. Instead of taking whole 3D volumes as inputs, we adapt axial patches and customize patch-wise queries to ensure semantic consistency. Additionally, we conducted extensive experiments on the BTCV and ACDC datasets, achieving improvements up to 11.48% and 6.71% respectively in mDSC, compared to state-of-the-art methods. Lastly, our proposed method demonstrates outstanding efficiency, reducing the number of parameters by 36.7% and the number of FLOPS by 10.7% compared to UNETR. This advancement holds promising potential for adapting our method to real-world clinical practice. The code will be available at https://github.com/goblin327/SegStitch

Yingfan Liu, Tong Wu, Jiadong Xie et al.

Approximate nearest neighbor (ANN) search with range filters has recently garnered significant attention. This paper delves into a generalized form of this problem, i.e., ANN search with exact range-range (RR) predicates on a range-valued attribute, named RR filtering ANN (RRANN). Specifically, given $n$ vectors in $\mathbb{R}^d$, each vector $v_i$ is associated with a numeric range $[l_i, r_i]$, symbolizing aspects like a price range or time interval. An RRANN query $(v_q, l_q, r_q)$ aims at finding $k$ vectors closest to $v_q$ within the vectors satisfying an arbitrary RR predicate defined between the query range $[l_q, r_q]$ and the object range $[l_i, r_i]$. The RR predicate remains unspecified, enabling user-defined conditions. It may encompass containment ($[l_i, r_i] \subseteq [l_q, r_q]$ or $[l_q, r_q] \subseteq [l_i, r_i]$), overlap ($l_i \le l_q \le r_i \le r_q$ or $l_q \le l_i \le r_q \le r_i$), or a disjunction of them. RRANN has broad applications in queries related to price ranges or time intervals, and it generalizes existing variants of ANN search with range filters. However, existing dedicated approaches for these problems lack the capacity to support queries with arbitrary RR predicates. Hence, we introduce a new approach, labeled multi-segment tree graph. It efficiently handles arbitrary RR predicates by avoiding traversal through non-predicate-satisfied nodes, and keeps equivalent index size and construction time to state-of-the-art methods for RFANN. Extensive experiments on real-world data demonstrate the efficacy of our approach in RRANN queries, achieving up to 12.5x speedups with the same accuracy as the baselines. Moreover, our approach attains comparable RFANN search performance and notably superior IFANN and TSANN search performance compared to the respective state-of-the-art approaches. Our code is available at https://github.com/FanEDG/MSTG.

Susie Xi Rao, Clémence Lanfranchi, Shuai Zhang et al. · amazon-science, eth-zurich

At online retail platforms, detecting fraudulent accounts and transactions is crucial to improve customer experience, minimize loss, and avoid unauthorized transactions. Despite the variety of different models for deep learning on graphs, few approaches have been proposed for dealing with graphs that are both heterogeneous and dynamic. In this paper, we propose DyHGN (Dynamic Heterogeneous Graph Neural Network) and its variants to capture both temporal and heterogeneous information. We first construct dynamic heterogeneous graphs from registration and transaction data from eBay. Then, we build models with diachronic entity embedding and heterogeneous graph transformer. We also use model explainability techniques to understand the behaviors of DyHGN-* models. Our findings reveal that modelling graph dynamics with heterogeneous inputs need to be conducted with "attention" depending on the data structure, distribution, and computation cost.

Bin Wang, Yan Song, Fanming Wang et al.

To balance the annotation labor and the granularity of supervision, single-frame annotation has been introduced in temporal action localization. It provides a rough temporal location for an action but implicitly overstates the supervision from the annotated-frame during training, leading to the confusion between actions and backgrounds, i.e., action incompleteness and background false positives. To tackle the two challenges, in this work, we present the Snippet Classification model and the Dilation-Erosion module. In the Dilation-Erosion module, we expand the potential action segments with a loose criterion to alleviate the problem of action incompleteness and then remove the background from the potential action segments to alleviate the problem of action incompleteness. Relying on the single-frame annotation and the output of the snippet classification, the Dilation-Erosion module mines pseudo snippet-level ground-truth, hard backgrounds and evident backgrounds, which in turn further trains the Snippet Classification model. It forms a cyclic dependency. Furthermore, we propose a new embedding loss to aggregate the features of action instances with the same label and separate the features of actions from backgrounds. Experiments on THUMOS14 and ActivityNet 1.2 validate the effectiveness of the proposed method. Code has been made publicly available (https://github.com/LingJun123/single-frame-TAL).

Xuhui Jia, Yang Zhao, Kelvin C. K. Chan et al.

This paper proposes a method for generating images of customized objects specified by users. The method is based on a general framework that bypasses the lengthy optimization required by previous approaches, which often employ a per-object optimization paradigm. Our framework adopts an encoder to capture high-level identifiable semantics of objects, producing an object-specific embedding with only a single feed-forward pass. The acquired object embedding is then passed to a text-to-image synthesis model for subsequent generation. To effectively blend a object-aware embedding space into a well developed text-to-image model under the same generation context, we investigate different network designs and training strategies, and propose a simple yet effective regularized joint training scheme with an object identity preservation loss. Additionally, we propose a caption generation scheme that become a critical piece in fostering object specific embedding faithfully reflected into the generation process, while keeping control and editing abilities. Once trained, the network is able to produce diverse content and styles, conditioned on both texts and objects. We demonstrate through experiments that our proposed method is able to synthesize images with compelling output quality, appearance diversity, and object fidelity, without the need of test-time optimization. Systematic studies are also conducted to analyze our models, providing insights for future work.

Longguang Wang, Yulan Guo, Juncheng Li et al.

This paper summarizes the 3rd NTIRE challenge on stereo image super-resolution (SR) with a focus on new solutions and results. The task of this challenge is to super-resolve a low-resolution stereo image pair to a high-resolution one with a magnification factor of x4 under a limited computational budget. Compared with single image SR, the major challenge of this challenge lies in how to exploit additional information in another viewpoint and how to maintain stereo consistency in the results. This challenge has 2 tracks, including one track on bicubic degradation and one track on real degradations. In total, 108 and 70 participants were successfully registered for each track, respectively. In the test phase, 14 and 13 teams successfully submitted valid results with PSNR (RGB) scores better than the baseline. This challenge establishes a new benchmark for stereo image SR.

Yang Zhao, Zhijie Lin, Daquan Zhou et al.

LLMs have demonstrated remarkable abilities at interacting with humans through language, especially with the usage of instruction-following data. Recent advancements in LLMs, such as MiniGPT-4, LLaVA, and X-LLM, further enlarge their abilities by incorporating multi-modal inputs, including image, video, and speech. Despite their effectiveness at generating precise and detailed language understanding of the given modality signal, these LLMs give up the ability to ground specific parts of inputs, thus only constructing a coarse-grained mapping. However, explicit and informative correspondence between text and other modalities will not only improve the user experience but also help to expand the application scenario of multi-modal LLMs. Therefore, we propose BuboGPT, a multi-modal LLM with visual grounding that can perform cross-modal interaction between vision, audio and language, providing fine-grained understanding of visual objects and other given modalities. As a result, BuboGPT is able to point out the specific location of an object in the image, when it is generating response or description for that object. Our contributions are two-fold: 1) An off-the-shelf visual grounding module based on SAM that extracts entities in a sentence and find corresponding masks in the image. 2) A two-stage training scheme and instruction dataset to endow joint text-image-audio understanding. Our experiments show that BuboGPT achieves impressive multi-modality understanding and visual grounding abilities during the interaction with human. It performs consistently well when provided by arbitrary modality combinations (either aligned or unaligned). Our code, model and dataset are available at https://bubo-gpt.github.io .

Yang Zhao, Jiaxi Yang, Wenbo Wang et al.

Industrial systems demand reliable predictive maintenance strategies to enhance operational efficiency and reduce downtime. This paper introduces an integrated framework that leverages the capabilities of the Transformer model-based neural networks and deep reinforcement learning (DRL) algorithms to optimize system maintenance actions. Our approach employs the Transformer model to effectively capture complex temporal patterns in sensor data, thereby accurately predicting the remaining useful life (RUL) of an equipment. Additionally, the DRL component of our framework provides cost-effective and timely maintenance recommendations. We validate the efficacy of our framework on the NASA C-MPASS dataset, where it demonstrates significant advancements in both RUL prediction accuracy and the optimization of maintenance actions, compared to the other prevalent machine learning-based methods. Our proposed approach provides an innovative data-driven framework for industry machine systems, accurately forecasting equipment lifespans and optimizing maintenance schedules, thereby reducing downtime and cutting costs.

Haoran You, Zhanyi Sun, Huihong Shi et al.

Vision Transformers (ViTs) have achieved state-of-the-art performance on various vision tasks. However, ViTs' self-attention module is still arguably a major bottleneck, limiting their achievable hardware efficiency. Meanwhile, existing accelerators dedicated to NLP Transformers are not optimal for ViTs. This is because there is a large difference between ViTs and NLP Transformers: ViTs have a relatively fixed number of input tokens, whose attention maps can be pruned by up to 90% even with fixed sparse patterns; while NLP Transformers need to handle input sequences of varying numbers of tokens and rely on on-the-fly predictions of dynamic sparse attention patterns for each input to achieve a decent sparsity (e.g., >=50%). To this end, we propose a dedicated algorithm and accelerator co-design framework dubbed ViTCoD for accelerating ViTs. Specifically, on the algorithm level, ViTCoD prunes and polarizes the attention maps to have either denser or sparser fixed patterns for regularizing two levels of workloads without hurting the accuracy, largely reducing the attention computations while leaving room for alleviating the remaining dominant data movements; on top of that, we further integrate a lightweight and learnable auto-encoder module to enable trading the dominant high-cost data movements for lower-cost computations. On the hardware level, we develop a dedicated accelerator to simultaneously coordinate the enforced denser/sparser workloads and encoder/decoder engines for boosted hardware utilization. Extensive experiments and ablation studies validate that ViTCoD largely reduces the dominant data movement costs, achieving speedups of up to 235.3x, 142.9x, 86.0x, 10.1x, and 6.8x over general computing platforms CPUs, EdgeGPUs, GPUs, and prior-art Transformer accelerators SpAtten and Sanger under an attention sparsity of 90%, respectively.

Haoyuan Li, Hao Jiang, Tao Jin et al.

Product Retrieval (PR) and Grounding (PG), aiming to seek image and object-level products respectively according to a textual query, have attracted great interest recently for better shopping experience. Owing to the lack of relevant datasets, we collect two large-scale benchmark datasets from Taobao Mall and Live domains with about 474k and 101k image-query pairs for PR, and manually annotate the object bounding boxes in each image for PG. As annotating boxes is expensive and time-consuming, we attempt to transfer knowledge from annotated domain to unannotated for PG to achieve un-supervised Domain Adaptation (PG-DA). We propose a {\bf D}omain {\bf A}daptive Produc{\bf t} S{\bf e}eker ({\bf DATE}) framework, regarding PR and PG as Product Seeking problem at different levels, to assist the query {\bf date} the product. Concretely, we first design a semantics-aggregated feature extractor for each modality to obtain concentrated and comprehensive features for following efficient retrieval and fine-grained grounding tasks. Then, we present two cooperative seekers to simultaneously search the image for PR and localize the product for PG. Besides, we devise a domain aligner for PG-DA to alleviate uni-modal marginal and multi-modal conditional distribution shift between source and target domains, and design a pseudo box generator to dynamically select reliable instances and generate bounding boxes for further knowledge transfer. Extensive experiments show that our DATE achieves satisfactory performance in fully-supervised PR, PG and un-supervised PG-DA. Our desensitized datasets will be publicly available here\footnote{\url{https://github.com/Taobao-live/Product-Seeking}}.

Sina Dehghan, Tiebiao Zhao, Yang Zhao et al.

This paper presents a multi-variable Model Predictive Control (MPC) based controller for the one-staged refrigeration cycle model described in the PID2018 Benchmark Challenge. This model represents a two-input, two-output system with strong nonlinearities and high coupling between its variables. A general purpose optimal control problem (OCP) solver Matlab toolbox called RIOTS is used as the OCP solver for the proposed MPC scheme which allows for straightforward implementation of the method and for solving a wide range of constrained linear and nonlinear optimal control problems. A conditional integral (CI) compensator is embedded in the controller to compensate for the small steady state errors. This method shows significant improvements in performance compared to both discrete decentralized control (C1) and multi-variable PID controller (C2) originally given in PID2018 Benchmark Challenge as a baseline. Our solution is introduced in detail in this paper and our final results using the overall relative index, $J$, are 0.2 over C1 and 0.3 over C2, respectively. In other words, we achieved 80% improvement over C1 and 70% improvement over C2. We expect to achieve further improvements when some optimized searching efforts are used for MPC and CI parameter tuning.

Yang Zhao, Gangwei Xu, Gang Wu

Current state-of-the-art flow methods are mostly based on dense all-pairs cost volumes. However, as image resolution increases, the computational and spatial complexity of constructing these cost volumes grows at a quartic rate, making these methods impractical for high-resolution images. In this paper, we propose a novel Hybrid Cost Volume for memory-efficient optical flow, named HCV. To construct HCV, we first propose a Top-k strategy to separate the 4D cost volume into two global 3D cost volumes. These volumes significantly reduce memory usage while retaining a substantial amount of matching information. We further introduce a local 4D cost volume with a local search space to supplement the local information for HCV. Based on HCV, we design a memory-efficient optical flow network, named HCVFlow. Compared to the recurrent flow methods based the all-pairs cost volumes, our HCVFlow significantly reduces memory consumption while ensuring high accuracy. We validate the effectiveness and efficiency of our method on the Sintel and KITTI datasets and real-world 4K (2160*3840) resolution images. Extensive experiments show that our HCVFlow has very low memory usage and outperforms other memory-efficient methods in terms of accuracy. The code is publicly available at https://github.com/gangweiX/HCVFlow.

Jie Yuan, Abdullah Ates, Sina Dehghan et al.

Since proportional-integral-derivative (PID) controllers absolutely dominate the control engineering, numbers of different control structures and theories have been developed to enhance the efficiency of PID controllers. Thus, it is essential and inspiring to operate different PID control strategies to the PID2018 Benchmark Challenge. In this paper, a novel control strategy is designed for this refrigeration system, where a feedforward compensator and a conditional integrator are utilized to compensate the disturbances and remove the steady-state error in the benchmark problem, respectively. The simulation results given in the benchmark problem show the straightforward effectiveness of the proposed control structure compared with the existing control methods.

Zehan Wang, Haifeng Huang, Yang Zhao et al.

3D scene understanding has gained significant attention due to its wide range of applications. However, existing methods for 3D scene understanding are limited to specific downstream tasks, which hinders their practicality in real-world applications. This paper presents Chat-3D, which combines the 3D visual perceptual ability of pre-trained 3D representations and the impressive reasoning and conversation capabilities of advanced LLMs to achieve the first universal dialogue systems for 3D scenes. Specifically, we align 3D representations into the feature space of LLMs, thus enabling LLMs to perceive the 3D world. Given the scarcity of 3D scene-text data, we propose a three-stage training strategy to efficiently utilize the available data for better alignment. To enhance the reasoning ability and develop a user-friendly interaction scheme, we further construct a high-quality object-centric 3D instruction dataset and design an associated object-centric prompt. Our experiments show that Chat-3D achieves an impressive ability to comprehend diverse instructions for 3D scenes, engage in intricate spatial reasoning, and incorporate external knowledge into its responses. Chat-3D achieves a 75.6% relative score compared with GPT-4 on the constructed instruction dataset.

Yang Zhao, Hao Zhang, Xiuyuan Hu · tsinghua

By driving models to converge to flat minima, sharpness-aware learning algorithms (such as SAM) have shown the power to achieve state-of-the-art performances. However, these algorithms will generally incur one extra forward-backward propagation at each training iteration, which largely burdens the computation especially for scalable models. To this end, we propose a simple yet efficient training scheme, called Randomized Sharpness-Aware Training (RST). Optimizers in RST would perform a Bernoulli trial at each iteration to choose randomly from base algorithms (SGD) and sharpness-aware algorithms (SAM) with a probability arranged by a predefined scheduling function. Due to the mixture of base algorithms, the overall count of propagation pairs could be largely reduced. Also, we give theoretical analysis on the convergence of RST. Then, we empirically study the computation cost and effect of various types of scheduling functions, and give directions on setting appropriate scheduling functions. Further, we extend the RST to a general framework (G-RST), where we can adjust regularization degree on sharpness freely for any scheduling function. We show that G-RST can outperform SAM in most cases while saving 50\% extra computation cost.

Weide Liu, Zhonghua Wu, Yang Zhao et al.

Current methods for few-shot segmentation (FSSeg) have mainly focused on improving the performance of novel classes while neglecting the performance of base classes. To overcome this limitation, the task of generalized few-shot semantic segmentation (GFSSeg) has been introduced, aiming to predict segmentation masks for both base and novel classes. However, the current prototype-based methods do not explicitly consider the relationship between base and novel classes when updating prototypes, leading to a limited performance in identifying true categories. To address this challenge, we propose a class contrastive loss and a class relationship loss to regulate prototype updates and encourage a large distance between prototypes from different classes, thus distinguishing the classes from each other while maintaining the performance of the base classes. Our proposed approach achieves new state-of-the-art performance for the generalized few-shot segmentation task on PASCAL VOC and MS COCO datasets.

Zehan Wang, Haifeng Huang, Yang Zhao et al.

3D visual grounding aims to localize the target object in a 3D point cloud by a free-form language description. Typically, the sentences describing the target object tend to provide information about its relative relation between other objects and its position within the whole scene. In this work, we propose a relation-aware one-stage framework, named 3D Relative Position-aware Network (3DRP-Net), which can effectively capture the relative spatial relationships between objects and enhance object attributes. Specifically, 1) we propose a 3D Relative Position Multi-head Attention (3DRP-MA) module to analyze relative relations from different directions in the context of object pairs, which helps the model to focus on the specific object relations mentioned in the sentence. 2) We designed a soft-labeling strategy to alleviate the spatial ambiguity caused by redundant points, which further stabilizes and enhances the learning process through a constant and discriminative distribution. Extensive experiments conducted on three benchmarks (i.e., ScanRefer and Nr3D/Sr3D) demonstrate that our method outperforms all the state-of-the-art methods in general. The source code will be released on GitHub.

Zehan Wang, Haifeng Huang, Yang Zhao et al.

3D visual grounding involves finding a target object in a 3D scene that corresponds to a given sentence query. Although many approaches have been proposed and achieved impressive performance, they all require dense object-sentence pair annotations in 3D point clouds, which are both time-consuming and expensive. To address the problem that fine-grained annotated data is difficult to obtain, we propose to leverage weakly supervised annotations to learn the 3D visual grounding model, i.e., only coarse scene-sentence correspondences are used to learn object-sentence links. To accomplish this, we design a novel semantic matching model that analyzes the semantic similarity between object proposals and sentences in a coarse-to-fine manner. Specifically, we first extract object proposals and coarsely select the top-K candidates based on feature and class similarity matrices. Next, we reconstruct the masked keywords of the sentence using each candidate one by one, and the reconstructed accuracy finely reflects the semantic similarity of each candidate to the query. Additionally, we distill the coarse-to-fine semantic matching knowledge into a typical two-stage 3D visual grounding model, which reduces inference costs and improves performance by taking full advantage of the well-studied structure of the existing architectures. We conduct extensive experiments on ScanRefer, Nr3D, and Sr3D, which demonstrate the effectiveness of our proposed method.

Abdullah Ates, Jie Yuan, Sina Dehghan et al.

This paper presents a multi-objective stochastic optimization method for tuning of the controller parameters of Refrigeration Systems based on Vapour Compression. Stochastic Multi Parameter Divergence Optimization (SMDO) algorithm is modified for minimization of the Multi Objective function for optimization process. System control performance is improved by tuning of the PI controller parameters according to discrete time model of the refrigeration system with multi objective function by adding conditional integral structure that is preferred to reduce the steady state error of the system. Simulations are compared with existing results via many graphical and numerical solutions.

Yang Zhao, Sina Dehghan, Abdullah Ates et al.

The design and application of learning feedforward controllers (LFFC) for the one-staged refrigeration cycle model described in the PID2018 Benchmark Challenge is presented, and its effectiveness is evaluated. The control system consists of two components: 1) a preset PID component and 2) a learning feedforward component which is a function approximator that is adapted on the basis of the feedback signal. A B-spline network based LFFC and a low-pass filter based LFFC are designed to track the desired outlet temperature of evaporator secondary flux and the superheating degree of refrigerant at evaporator outlet. Encouraging simulation results are included. Qualitative and quantitative comparison results evaluations show that, with little effort, a high-performance control system can be obtained with this approach. Our initial simple attempt of low-pass filter based LFFC and B-spline network based LFFC give J=0.4902 and J=0.6536 relative to the decentralized PID controller, respectively. Besides, the initial attempt of a combination controller of our optimized PI controller and low-pass filter LFFC gives J=0.6947 relative to the multi-variable PID controller.

Yuxiang Guo, Faizan Siddiqui, Yang Zhao et al.

Predicting and reasoning how a video would make a human feel is crucial for developing socially intelligent systems. Although Multimodal Large Language Models (MLLMs) have shown impressive video understanding capabilities, they tend to focus more on the semantic content of videos, often overlooking emotional stimuli. Hence, most existing MLLMs fall short in estimating viewers' emotional reactions and providing plausible explanations. To address this issue, we propose StimuVAR, a spatiotemporal Stimuli-aware framework for Video Affective Reasoning (VAR) with MLLMs. StimuVAR incorporates a two-level stimuli-aware mechanism: frame-level awareness and token-level awareness. Frame-level awareness involves sampling video frames with events that are most likely to evoke viewers' emotions. Token-level awareness performs tube selection in the token space to make the MLLM concentrate on emotion-triggered spatiotemporal regions. Furthermore, we create VAR instruction data to perform affective training, steering MLLMs' reasoning strengths towards emotional focus and thereby enhancing their affective reasoning ability. To thoroughly assess the effectiveness of VAR, we provide a comprehensive evaluation protocol with extensive metrics. StimuVAR is the first MLLM-based method for viewer-centered VAR. Experiments demonstrate its superiority in understanding viewers' emotional responses to videos and providing coherent and insightful explanations. Our code is available at https://github.com/EthanG97/StimuVAR

Yu-Chuan Su, Kelvin C. K. Chan, Yandong Li et al.

Many applications can benefit from personalized image generation models, including image enhancement, video conferences, just to name a few. Existing works achieved personalization by fine-tuning one model for each person. While being successful, this approach incurs additional computation and storage overhead for each new identity. Furthermore, it usually expects tens or hundreds of examples per identity to achieve the best performance. To overcome these challenges, we propose an encoder-based approach for personalization. We learn an identity encoder which can extract an identity representation from a set of reference images of a subject, together with a diffusion generator that can generate new images of the subject conditioned on the identity representation. Once being trained, the model can be used to generate images of arbitrary identities given a few examples even if the model hasn't been trained on the identity. Our approach greatly reduces the overhead for personalized image generation and is more applicable in many potential applications. Empirical results show that our approach consistently outperforms existing fine-tuning based approach in both image generation and reconstruction, and the outputs is preferred by users more than 95% of the time compared with the best performing baseline.

Khoa D. Doan, Jianwen Xie, Yaxuan Zhu et al. · baidu

Leveraging supervised information can lead to superior retrieval performance in the image hashing domain but the performance degrades significantly without enough labeled data. One effective solution to boost performance is to employ generative models, such as Generative Adversarial Networks (GANs), to generate synthetic data in an image hashing model. However, GAN-based methods are difficult to train, which prevents the hashing approaches from jointly training the generative models and the hash functions. This limitation results in sub-optimal retrieval performance. To overcome this limitation, we propose a novel framework, the generative cooperative hashing network, which is based on energy-based cooperative learning. This framework jointly learns a powerful generative representation of the data and a robust hash function via two components: a top-down contrastive pair generator that synthesizes contrastive images and a bottom-up multipurpose descriptor that simultaneously represents the images from multiple perspectives, including probability density, hash code, latent code, and category. The two components are jointly learned via a novel likelihood-based cooperative learning scheme. We conduct experiments on several real-world datasets and show that the proposed method outperforms the competing hashing supervised methods, achieving up to 10\% relative improvement over the current state-of-the-art supervised hashing methods, and exhibits a significantly better performance in out-of-distribution retrieval.

Yang Zhao, Peng Guo, Han Gao et al.

Unsupervised domain adaptation (UDA) is an approach to minimizing domain gap. Generative methods are common approaches to minimizing the domain gap of aerial images which improves the performance of the downstream tasks, e.g., cross-domain semantic segmentation. For aerial images, the digital surface model (DSM) is usually available in both the source domain and the target domain. Depth information in DSM brings external information to generative models. However, little research utilizes it. In this paper, depth-assisted ResiDualGAN (DRDG) is proposed where depth supervised loss (DSL), and depth cycle consistency loss (DCCL) are used to bring depth information into the generative model. Experimental results show that DRDG reaches state-of-the-art accuracy between generative methods in cross-domain semantic segmentation tasks.

Zhonghao Wang, Wei Wei, Yang Zhao et al.

This paper explores advancements in high-fidelity personalized image generation through the utilization of pre-trained text-to-image diffusion models. While previous approaches have made significant strides in generating versatile scenes based on text descriptions and a few input images, challenges persist in maintaining the subject fidelity within the generated images. In this work, we introduce an innovative algorithm named HiFi Tuner to enhance the appearance preservation of objects during personalized image generation. Our proposed method employs a parameter-efficient fine-tuning framework, comprising a denoising process and a pivotal inversion process. Key enhancements include the utilization of mask guidance, a novel parameter regularization technique, and the incorporation of step-wise subject representations to elevate the sample fidelity. Additionally, we propose a reference-guided generation approach that leverages the pivotal inversion of a reference image to mitigate unwanted subject variations and artifacts. We further extend our method to a novel image editing task: substituting the subject in an image through textual manipulations. Experimental evaluations conducted on the DreamBooth dataset using the Stable Diffusion model showcase promising results. Fine-tuning solely on textual embeddings improves CLIP-T score by 3.6 points and improves DINO score by 9.6 points over Textual Inversion. When fine-tuning all parameters, HiFi Tuner improves CLIP-T score by 1.2 points and improves DINO score by 1.2 points over DreamBooth, establishing a new state of the art.

Yuqing Wang, Zhijie Lin, Ceyuan Yang et al.

Unified multimodal models (UMMs) aim to handle perception and generation in a single model. Yet existing UMMs still rely on a frozen, separately pretrained VAE for image generation, imposing a structural bottleneck. Naively removing it introduces a quality gap, as the model must learn both high-level structure and low-level details from raw pixels. In this paper, we propose Representation Forcing (RF), a technique that closes this gap by making representation prediction a native capability of the model. Concretely, RF forces the decoder to autoregressively predict visual representations as intermediate tokens before pixels; these tokens then stay in context to guide pixel diffusion within the same backbone. By turning representations from perception outputs into generation targets, RF eliminates the need for any external generative latent space. We find that RF benefits both understanding and generation. On image generation, our pixel-space model with RF matches state-of-the-art VAE-based unified models. On image understanding, pixel-space RF generally outperforms its VAE-based variant. Together, these results offer an effective step toward end-to-end, bottleneck-free UMMs.

Guanting Dong, Junting Lu, Junjie Huang et al.

Large language models are increasingly expected to serve as general-purpose agents that interact with external, stateful tool environments. The Model Context Protocol (MCP) and broader agent skills offer a unified interface for connecting agents with scalable real-world services, but training robust agents remains limited by the lack of realistic environments and principled mechanisms for life-long learning. In this paper, we present \textbf{Agent-World}, a self-evolving training arena for advancing general agent intelligence through scalable environments. Agent-World has two main components: (1) Agentic Environment-Task Discovery, which autonomously explores topic-aligned databases and executable tool ecosystems from thousands of real-world environment themes and synthesizes verifiable tasks with controllable difficulty; and (2) Continuous Self-Evolving Agent Training, which combines multi-environment reinforcement learning with a self-evolving agent arena that automatically identifies capability gaps through dynamic task synthesis and drives targeted learning, enabling the co-evolution of agent policies and environments. Across 23 challenging agent benchmarks, Agent-World-8B and 14B consistently outperforms strong proprietary models and environment scaling baselines. Further analyses reveal scaling trends in relation to environment diversity and self-evolution rounds, offering insights for building general agent intelligence.

Yanwu Xu, Yang Zhao, Zhisheng Xiao et al.

Text-to-image diffusion models have demonstrated remarkable capabilities in transforming textual prompts into coherent images, yet the computational cost of their inference remains a persistent challenge. To address this issue, we present UFOGen, a novel generative model designed for ultra-fast, one-step text-to-image synthesis. In contrast to conventional approaches that focus on improving samplers or employing distillation techniques for diffusion models, UFOGen adopts a hybrid methodology, integrating diffusion models with a GAN objective. Leveraging a newly introduced diffusion-GAN objective and initialization with pre-trained diffusion models, UFOGen excels in efficiently generating high-quality images conditioned on textual descriptions in a single step. Beyond traditional text-to-image generation, UFOGen showcases versatility in applications. Notably, UFOGen stands among the pioneering models enabling one-step text-to-image generation and diverse downstream tasks, presenting a significant advancement in the landscape of efficient generative models.

Yanyan Wei, Zhao Zhang, Zhongqiu Zhao et al.

Stereo images, containing left and right view images with disparity, are utilized in solving low-vision tasks recently, e.g., rain removal and super-resolution. Stereo image restoration methods usually obtain better performance than monocular methods by learning the disparity between dual views either implicitly or explicitly. However, existing stereo rain removal methods still cannot make full use of the complementary information between two views, and we find it is because: 1) the rain streaks have more complex distributions in directions and densities, which severely damage the complementary information and pose greater challenges; 2) the disparity estimation is not accurate enough due to the imperfect fusion mechanism for the features between two views. To overcome such limitations, we propose a new \underline{Stereo} \underline{I}mage \underline{R}ain \underline{R}emoval method (StereoIRR) via sufficient interaction between two views, which incorporates: 1) a new Dual-view Mutual Attention (DMA) mechanism which generates mutual attention maps by taking left and right views as key information for each other to facilitate cross-view feature fusion; 2) a long-range and cross-view interaction, which is constructed with basic blocks and dual-view mutual attention, can alleviate the adverse effect of rain on complementary information to help the features of stereo images to get long-range and cross-view interaction and fusion. Notably, StereoIRR outperforms other related monocular and stereo image rain removal methods on several datasets. Our codes and datasets will be released.

Yang Zhao, Junnan Zhu, Lu Xiang et al.

A common scenario of Multilingual Neural Machine Translation (MNMT) is that each translation task arrives in a sequential manner, and the training data of previous tasks is unavailable. In this scenario, the current methods suffer heavily from catastrophic forgetting (CF). To alleviate the CF, we investigate knowledge distillation based life-long learning methods. Specifically, in one-tomany scenario, we propose a multilingual distillation method to make the new model (student) jointly learn multilingual output from old model (teacher) and new task. In many-to one scenario, we find that direct distillation faces the extreme partial distillation problem, and we propose two different methods to address it: pseudo input distillation and reverse teacher distillation. The experimental results on twelve translation tasks show that the proposed methods can better consolidate the previous knowledge and sharply alleviate the CF.

Yang Zhao, Tingbo Hou, Yu-Chuan Su et al.

An authentic face restoration system is becoming increasingly demanding in many computer vision applications, e.g., image enhancement, video communication, and taking portrait. Most of the advanced face restoration models can recover high-quality faces from low-quality ones but usually fail to faithfully generate realistic and high-frequency details that are favored by users. To achieve authentic restoration, we propose $\textbf{IDM}$, an $\textbf{I}$teratively learned face restoration system based on denoising $\textbf{D}$iffusion $\textbf{M}$odels (DDMs). We define the criterion of an authentic face restoration system, and argue that denoising diffusion models are naturally endowed with this property from two aspects: intrinsic iterative refinement and extrinsic iterative enhancement. Intrinsic learning can preserve the content well and gradually refine the high-quality details, while extrinsic enhancement helps clean the data and improve the restoration task one step further. We demonstrate superior performance on blind face restoration tasks. Beyond restoration, we find the authentically cleaned data by the proposed restoration system is also helpful to image generation tasks in terms of training stabilization and sample quality. Without modifying the models, we achieve better quality than state-of-the-art on FFHQ and ImageNet generation using either GANs or diffusion models.

Yan Xia, Zhou Zhao, Shangwei Ye et al.

In this paper, we introduce a new task, spoken video grounding (SVG), which aims to localize the desired video fragments from spoken language descriptions. Compared with using text, employing audio requires the model to directly exploit the useful phonemes and syllables related to the video from raw speech. Moreover, we randomly add environmental noises to this speech audio, further increasing the difficulty of this task and better simulating real applications. To rectify the discriminative phonemes and extract video-related information from noisy audio, we develop a novel video-guided curriculum learning (VGCL) during the audio pre-training process, which can make use of the vital visual perceptions to help understand the spoken language and suppress the external noise. Considering during inference the model can not obtain ground truth video segments, we design a curriculum strategy that gradually shifts the input video from the ground truth to the entire video content during pre-training. Finally, the model can learn how to extract critical visual information from the entire video clip to help understand the spoken language. In addition, we collect the first large-scale spoken video grounding dataset based on ActivityNet, which is named as ActivityNet Speech dataset. Extensive experiments demonstrate our proposed video-guided curriculum learning can facilitate the pre-training process to obtain a mutual audio encoder, significantly promoting the performance of spoken video grounding tasks. Moreover, we prove that in the case of noisy sound, our model outperforms the method that grounding video with ASR transcripts, further demonstrating the effectiveness of our curriculum strategy.

Peisong Niu, Haifan Zhang, Yang Zhao et al.

Tropical cyclones (TCs) pose severe threats to life, infrastructure, and economies in tropical and subtropical regions, underscoring the critical need for accurate and timely forecasts of both track and intensity. Recent advances in AI-based weather forecasting have shown promise in improving TC track forecasts. However, these systems are typically trained on coarse-resolution reanalysis data (e.g., ERA5 at 0.25 degree), which constrains predicted TC positions to a fixed grid and introduces significant discretization errors. Moreover, intensity forecasting remains limited especially for strong TCs by the smoothing effect of coarse meteorological fields and the use of regression losses that bias predictions toward conditional means. To address these limitations, we propose BaguanCyclone, a novel, unified framework that integrates two key innovations: (1) a probabilistic center refinement module that models the continuous spatial distribution of TC centers, enabling finer track precision; and (2) a region-aware intensity forecasting module that leverages high-resolution internal representations within dynamically defined sub-grid zones around the TC core to better capture localized extremes. Evaluated on the global IBTrACS dataset across six major TC basins, our system consistently outperforms both operational numerical weather prediction (NWP) models and most AI-based baselines, delivering a substantial enhancement in forecast accuracy. Remarkably, BaguanCyclone excels in navigating meteorological complexities, consistently delivering accurate forecasts for re-intensification, sweeping arcs, twin cyclones, and meandering events. Our code is available at https://github.com/DAMO-DI-ML/Baguan-cyclone.

Cong Ma, Yaping Zhang, Mei Tu et al.

End-to-end text image translation (TIT), which aims at translating the source language embedded in images to the target language, has attracted intensive attention in recent research. However, data sparsity limits the performance of end-to-end text image translation. Multi-task learning is a non-trivial way to alleviate this problem via exploring knowledge from complementary related tasks. In this paper, we propose a novel text translation enhanced text image translation, which trains the end-to-end model with text translation as an auxiliary task. By sharing model parameters and multi-task training, our model is able to take full advantage of easily-available large-scale text parallel corpus. Extensive experimental results show our proposed method outperforms existing end-to-end methods, and the joint multi-task learning with both text translation and recognition tasks achieves better results, proving translation and recognition auxiliary tasks are complementary.

Yuan Chen, Zhiliang Ma, Yang Zhao

Although many effective models and real-world datasets have been presented for blind image quality assessment (BIQA), recent BIQA models usually tend to fit specific training set. Hence, it is still difficult to accurately and robustly measure the visual quality of an arbitrary real-world image. In this paper, a robust BIQA method, is designed based on three aspects, i.e., robust training strategy, large-scale real-world dataset, and powerful backbone. First, many individual models based on popular and state-of-the-art (SOTA) Swin-Transformer (SwinT) are trained on different real-world BIQA datasets respectively. Then, these biased SwinT-based models are jointly used to generate pseudo-labels, which adopts the probability of relative quality of two random images instead of fixed quality score. A large-scale real-world image dataset with 1,000,000 image pairs and pseudo-labels is then proposed for training the final cross-dataset-robust model. Experimental results on cross-dataset tests show that the performance of the proposed method is even better than some SOTA methods that are directly trained on these datasets, thus verifying the robustness and generalization of our method.

Zirui Zhang, Yaping Zhang, Lu Xiang et al.

Document Layout Analysis (DLA) is crucial for document artificial intelligence and has recently received increasing attention, resulting in an influx of large-scale public DLA datasets. Existing work often combines data from various domains in recent public DLA datasets to improve the generalization of DLA. However, directly merging these datasets for training often results in suboptimal model performance, as it overlooks the different layout structures inherent to various domains. These variations include different labeling styles, document types, and languages. This paper introduces PromptDLA, a domain-aware Prompter for Document Layout Analysis that effectively leverages descriptive knowledge as cues to integrate domain priors into DLA. The innovative PromptDLA features a unique domain-aware prompter that customizes prompts based on the specific attributes of the data domain. These prompts then serve as cues that direct the DLA toward critical features and structures within the data, enhancing the model's ability to generalize across varied domains. Extensive experiments show that our proposal achieves state-of-the-art performance among DocLayNet, PubLayNet, M6Doc, and D$^4$LA. Our code is available at https://github.com/Zirui00/PromptDLA.

Yang Zhao, Yanwu Xu, Zhisheng Xiao et al.

The deployment of large-scale text-to-image diffusion models on mobile devices is impeded by their substantial model size and slow inference speed. In this paper, we propose \textbf{MobileDiffusion}, a highly efficient text-to-image diffusion model obtained through extensive optimizations in both architecture and sampling techniques. We conduct a comprehensive examination of model architecture design to reduce redundancy, enhance computational efficiency, and minimize model's parameter count, while preserving image generation quality. Additionally, we employ distillation and diffusion-GAN finetuning techniques on MobileDiffusion to achieve 8-step and 1-step inference respectively. Empirical studies, conducted both quantitatively and qualitatively, demonstrate the effectiveness of our proposed techniques. MobileDiffusion achieves a remarkable \textbf{sub-second} inference speed for generating a $512\times512$ image on mobile devices, establishing a new state of the art.

Yang Zhao, Jungeun Lee, Jeong hwan Jeon et al.

Safety filters constructed from control barrier functions (CBFs) are commonly appended to pre-trained neural network controllers to enforce safety requirements. However, this decoupled design with hand-tuned, fixed CBF parameters often fails to adapt to the underlying controller, yielding overly conservative solutions. Thus, given a valid CBF, we address these limitations by jointly learning a neural network controller and neural-network-parameterized CBF parameters, enforcing the resulting affine safety constraints by construction and avoiding an online quadratic program (QP) safety filter at run time. To further improve computational efficiency and scalability, we introduce a lightweight projection architecture that enforces constraints without full constraint enumeration. Extensive simulation evaluations demonstrate reliable, scalable safety constraint satisfaction at reduced computational cost.

Zehan Wang, Ziang Zhang, Luping Liu et al.

Multi-modal contrastive representation (MCR) of more than three modalities is critical in multi-modal learning. Although recent methods showcase impressive achievements, the high dependence on large-scale, high-quality paired data and the expensive training costs limit their further development. Inspired by recent C-MCR, this paper proposes Extending Multimodal Contrastive Representation (Ex-MCR), a training-efficient and paired-data-free method to flexibly learn unified contrastive representation space for more than three modalities by integrating the knowledge of existing MCR spaces. Specifically, Ex-MCR aligns multiple existing MCRs into the same based MCR, which can effectively preserve the original semantic alignment of the based MCR. Besides, we comprehensively enhance the entire learning pipeline for aligning MCR spaces from the perspectives of training data, architecture, and learning objectives. With the preserved original modality alignment and the enhanced space alignment, Ex-MCR shows superior representation learning performance and excellent modality extensibility. To demonstrate the effectiveness of Ex-MCR, we align the MCR spaces of CLAP (audio-text) and ULIP (3D-vision) into the CLIP (vision-text), leveraging the overlapping text and image modality, respectively. Remarkably, without using any paired data, Ex-MCR learns a 3D-image-text-audio unified contrastive representation, and it achieves state-of-the-art performance on audio-visual, 3D-image, audio-text, visual-text retrieval, and 3D object classification tasks. More importantly, extensive qualitative results further demonstrate the emergent semantic alignment between the extended modalities (e.g., audio and 3D), which highlights the great potential of modality extensibility.

Zhichao Zuo, Zhao Zhang, Yan Luo et al.

This paper presents a novel framework termed Cut-and-Paste for real-word semantic video editing under the guidance of text prompt and additional reference image. While the text-driven video editing has demonstrated remarkable ability to generate highly diverse videos following given text prompts, the fine-grained semantic edits are hard to control by plain textual prompt only in terms of object details and edited region, and cumbersome long text descriptions are usually needed for the task. We therefore investigate subject-driven video editing for more precise control of both edited regions and background preservation, and fine-grained semantic generation. We achieve this goal by introducing an reference image as supplementary input to the text-driven video editing, which avoids racking your brain to come up with a cumbersome text prompt describing the detailed appearance of the object. To limit the editing area, we refer to a method of cross attention control in image editing and successfully extend it to video editing by fusing the attention map of adjacent frames, which strikes a balance between maintaining video background and spatio-temporal consistency. Compared with current methods, the whole process of our method is like ``cut" the source object to be edited and then ``paste" the target object provided by reference image. We demonstrate that our method performs favorably over prior arts for video editing under the guidance of text prompt and extra reference image, as measured by both quantitative and subjective evaluations.

Zeyu Zhang, Nengmin Yi, Shengbo Tan et al.

Cervical disc herniation (CDH) is a prevalent musculoskeletal disorder that significantly impacts health and requires labor-intensive analysis from experts. Despite advancements in automated detection of medical imaging, two significant challenges hinder the real-world application of these methods. First, the computational complexity and resource demands present a significant gap for real-time application. Second, noise in MRI reduces the effectiveness of existing methods by distorting feature extraction. To address these challenges, we propose three key contributions: Firstly, we introduced MedDet, which leverages the multi-teacher single-student knowledge distillation for model compression and efficiency, meanwhile integrating generative adversarial training to enhance performance. Additionally, we customize the second-order nmODE to improve the model's resistance to noise in MRI. Lastly, we conducted comprehensive experiments on the CDH-1848 dataset, achieving up to a 5% improvement in mAP compared to previous methods. Our approach also delivers over 5 times faster inference speed, with approximately 67.8% reduction in parameters and 36.9% reduction in FLOPs compared to the teacher model. These advancements significantly enhance the performance and efficiency of automated CDH detection, demonstrating promising potential for future application in clinical practice. See project website https://steve-zeyu-zhang.github.io/MedDet