Linlin Yang

Jiayin Zhu, Zhuoran Zhao, Linlin Yang et al.

We present HiFiHR, a high-fidelity hand reconstruction approach that utilizes render-and-compare in the learning-based framework from a single image, capable of generating visually plausible and accurate 3D hand meshes while recovering realistic textures. Our method achieves superior texture reconstruction by employing a parametric hand model with predefined texture assets, and by establishing a texture reconstruction consistency between the rendered and input images during training. Moreover, based on pretraining the network on an annotated dataset, we apply varying degrees of supervision using our pipeline, i.e., self-supervision, weak supervision, and full supervision, and discuss the various levels of contributions of the learned high-fidelity textures in enhancing hand pose and shape estimation. Experimental results on public benchmarks including FreiHAND and HO-3D demonstrate that our method outperforms the state-of-the-art hand reconstruction methods in texture reconstruction quality while maintaining comparable accuracy in pose and shape estimation. Our code is available at https://github.com/viridityzhu/HiFiHR.

Kerui Gu, Linlin Yang, Michael Bi Mi et al.

In human and hand pose estimation, heatmaps are a crucial intermediate representation for a body or hand keypoint. Two popular methods to decode the heatmap into a final joint coordinate are via an argmax, as done in heatmap detection, or via softmax and expectation, as done in integral regression. Integral regression is learnable end-to-end, but has lower accuracy than detection. This paper uncovers an induced bias from integral regression that results from combining the softmax and the expectation operation. This bias often forces the network to learn degenerately localized heatmaps, obscuring the keypoint's true underlying distribution and leads to lower accuracies. Training-wise, by investigating the gradients of integral regression, we show that the implicit guidance of integral regression to update the heatmap makes it slower to converge than detection. To counter the above two limitations, we propose Bias Compensated Integral Regression (BCIR), an integral regression-based framework that compensates for the bias. BCIR also incorporates a Gaussian prior loss to speed up training and improve prediction accuracy. Experimental results on both the human body and hand benchmarks show that BCIR is faster to train and more accurate than the original integral regression, making it competitive with state-of-the-art detection methods.

Ziwei Yu, Linlin Yang, You Xie et al.

We propose a novel framework for 3D hand shape reconstruction and hand-object grasp optimization from a single RGB image. The representation of hand-object contact regions is critical for accurate reconstructions. Instead of approximating the contact regions with sparse points, as in previous works, we propose a dense representation in the form of a UV coordinate map. Furthermore, we introduce inference-time optimization to fine-tune the grasp and improve interactions between the hand and the object. Our pipeline increases hand shape reconstruction accuracy and produces a vibrant hand texture. Experiments on datasets such as Ho3D, FreiHAND, and DexYCB reveal that our proposed method outperforms the state-of-the-art.

Huixin Sun, Yanjing Li, Linlin Yang et al.

Despite advances in generic object detection, there remains a performance gap in detecting small objects compared to normal-scale objects. We reveal that conventional object localization methods suffer from gradient instability in small objects due to sharper loss curvature, leading to a convergence challenge. To address the issue, we propose Uncertainty-Aware Gradient Stabilization (UGS), a framework that reformulates object localization as a classification task to stabilize gradients. UGS quantizes continuous labels into interval non-uniform discrete representations. Under a classification-based objective, the localization branch generates bounded and confidence-driven gradients, mitigating instability. Furthermore, UGS integrates an uncertainty minimization (UM) loss that reduces prediction variance and an uncertainty-guided refinement (UR) module that identifies and refines high-uncertainty regions via perturbations. Evaluated on four benchmarks, UGS consistently improves anchor-based, anchor-free, and leading small object detectors. Especially, UGS enhances DINO-5scale by 2.6 AP on VisDrone, surpassing previous state-of-the-art results.

Runqi Wang, Linlin Yang, Baochang Zhang et al.

Research on the generalization ability of deep neural networks (DNNs) has recently attracted a great deal of attention. However, due to their complex architectures and large numbers of parameters, measuring the generalization ability of specific DNN models remains an open challenge. In this paper, we propose to use multiple factors to measure and rank the relative generalization of DNNs based on a new concept of confidence dimension (CD). Furthermore, we provide a feasible framework in our CD to theoretically calculate the upper bound of generalization based on the conventional Vapnik-Chervonenk dimension (VC-dimension) and Hoeffding's inequality. Experimental results on image classification and object detection demonstrate that our CD can reflect the relative generalization ability for different DNNs. In addition to full-precision DNNs, we also analyze the generalization ability of binary neural networks (BNNs), whose generalization ability remains an unsolved problem. Our CD yields a consistent and reliable measure and ranking for both full-precision DNNs and BNNs on all the tasks.

Shihao Zhang, Linlin Yang, Michael Bi Mi et al.

In computer vision, it is often observed that formulating regression problems as a classification task often yields better performance. We investigate this curious phenomenon and provide a derivation to show that classification, with the cross-entropy loss, outperforms regression with a mean squared error loss in its ability to learn high-entropy feature representations. Based on the analysis, we propose an ordinal entropy loss to encourage higher-entropy feature spaces while maintaining ordinal relationships to improve the performance of regression tasks. Experiments on synthetic and real-world regression tasks demonstrate the importance and benefits of increasing entropy for regression.

Haodong Zhu, Yangyang Ren, Yanjing Li et al.

Group Relative Policy Optimization (GRPO) effectively scales LLM reasoning but incurs prohibitive computational costs due to its extensive group-based sampling requirement. While recent selective data utilization methods can mitigate this overhead, they could induce estimation bias by altering the underlying sampling distribution, compromising theoretical rigor and convergence behavior. To address this limitation, we propose Dynamic Pruning Policy Optimization (DPPO), a framework that enables dynamic pruning while preserving unbiased gradient estimation through importance sampling-based correction. By incorporating mathematically derived rescaling factors, DPPO significantly accelerates GRPO training without altering the optimization objective of the full-batch baseline. Furthermore, to mitigate the data sparsity induced by pruning, we introduce Dense Prompt Packing, a window-based greedy strategy that maximizes valid token density and hardware utilization. Extensive experiments demonstrate that DPPO consistently accelerates training across diverse models and benchmarks. For instance, on Qwen3-4B trained on MATH, DPPO achieves 2.37$\times$ training speedup and outperforms GRPO by 3.36% in average accuracy across six mathematical reasoning benchmarks.

Canyu Chen, Yuguang Yang, Zhewen Tan et al.

We identify a fundamental Narrow Policy limitation undermining the performance of autonomous VLA models, where driving Imitation Learning (IL) tends to collapse exploration and limit the potential of subsequent Reinforcement Learning (RL) stages, which often saturate prematurely due to insufficient feedback diversity. Thereby, we propose Curious-VLA, a framework that alleviates the exploit-explore dilemma through a two-stage design. During IL, we introduce a Feasible Trajectory Expansion (FTE) strategy to generate multiple physically valid trajectories and a step-wise normalized trajectory representation to adapt this diverse data. In the RL stage, we present Adaptive Diversity-Aware Sampling (ADAS) that prioritizes high-diversity samples and introduce Spanning Driving Reward (SDR) with a focal style weighting to amplify reward's value span for improving sensitivity to driving quality. On the Navsim benchmark, Curious-VLA achieves SoTA results (PDMS 90.3, EPDMS 85.4) and a Best-of-N PDMS of 94.8, demonstrating its effectiveness in unlocking the exploratory potential of VLA models. Code: https://github.com/Mashiroln/curious_vla.git.

Zihao Liu, Xiaoyu Wu, Jianqin Wu et al.

Video anomaly detection (VAD) aims to detect anomalies that deviate from what is expected. In open-world scenarios, the expected events may change as requirements change. For example, not wearing a mask may be considered abnormal during a flu outbreak but normal otherwise. However, existing methods assume that the definition of anomalies is invariable, and thus are not applicable to the open world. To address this, we propose a novel open-world VAD paradigm with variable definitions, allowing guided detection through user-provided natural language at inference time. This paradigm necessitates establishing a robust mapping from video and textual definition to anomaly scores. Therefore, we propose LaGoVAD (Language-guided Open-world Video Anomaly Detector), a model that dynamically adapts anomaly definitions under weak supervision with two regularization strategies: diversifying the relative durations of anomalies via dynamic video synthesis, and enhancing feature robustness through contrastive learning with negative mining. Training such adaptable models requires diverse anomaly definitions, but existing datasets typically provide labels without semantic descriptions. To bridge this gap, we collect PreVAD (Pre-training Video Anomaly Dataset), the largest and most diverse video anomaly dataset to date, featuring 35,279 annotated videos with multi-level category labels and descriptions that explicitly define anomalies. Zero-shot experiments on seven datasets demonstrate LaGoVAD's SOTA performance. Our dataset and code will be released at https://github.com/Kamino666/LaGoVAD-PreVAD.

Tongfei Chen, Shuo Yang, Yuguang Yang et al.

Referring Image Segmentation (RIS) aims to segment an object in an image identified by a natural language expression. The paper introduces Alignment-Aware Masked Learning (AML), a training strategy to enhance RIS by explicitly estimating pixel-level vision-language alignment, filtering out poorly aligned regions during optimization, and focusing on trustworthy cues. This approach results in state-of-the-art performance on RefCOCO datasets and also enhances robustness to diverse descriptions and scenarios

Yuxiang Bao, Guoliang Kang, Linlin Yang et al.

In real-world scenarios, the number of training samples across classes usually subjects to a long-tailed distribution. The conventionally trained network may achieve unexpected inferior performance on the rare class compared to the frequent class. Most previous works attempt to rectify the network bias from the data-level or from the classifier-level. Differently, in this paper, we identify that the bias towards the frequent class may be encoded into features, i.e., the rare-specific features which play a key role in discriminating the rare class are much weaker than the frequent-specific features. Based on such an observation, we introduce a simple yet effective approach, normalizing the parameters of Batch Normalization (BN) layer to explicitly rectify the feature bias. To achieve this end, we represent the Weight/Bias parameters of a BN layer as a vector, normalize it into a unit one and multiply the unit vector by a scalar learnable parameter. Through decoupling the direction and magnitude of parameters in BN layer to learn, the Weight/Bias exhibits a more balanced distribution and thus the strength of features becomes more even. Extensive experiments on various long-tailed recognition benchmarks (i.e., CIFAR-10/100-LT, ImageNet-LT and iNaturalist 2018) show that our method outperforms previous state-of-the-arts remarkably. The code and checkpoints are available at https://github.com/yuxiangbao/NBN.

Tongfei Chen, Jingying Yang, Linlin Yang et al.

Deep learning architectures are fundamentally inspired by neuroscience, particularly the structure of the brain's sensory pathways, and have achieved remarkable success in learning informative data representations. Although these architectures mimic the communication mechanisms of biological neurons, their strategies for information encoding and transmission are fundamentally distinct. Biological systems depend on dynamic fluctuations in membrane potential; by contrast, conventional deep networks optimize weights and biases by adjusting the strengths of inter-neural connections, lacking a systematic mechanism to jointly characterize the interplay among signal intensity, coupling structure, and state evolution. To tackle this limitation, we propose the Kirchhoff-Inspired Neural Network (KINN), a state-variable-based network architecture constructed based on Kirchhoff's current law. KINN derives numerically stable state updates from fundamental ordinary differential equations, enabling the explicit decoupling and encoding of higher-order evolutionary components within a single layer while preserving physical consistency, interpretability, and end-to-end trainability. Extensive experiments on partial differential equation (PDE) solving and ImageNet image classification validate that KINN outperforms state-of-the-art existing methods.

Zihao Liu, Xiaoyu Wu, Wenna Li et al.

Open-world video anomaly detection (OWVAD) aims to detect and explain abnormal events under different anomaly definitions, which is important for applications such as intelligent surveillance and live-streaming content moderation. Recent MLLM-based methods have shown promising open-world generalization, but still suffer from three major limitations: inefficiency for practical deployment, lack of streaming processing adaptation, and limited support for dynamic anomaly definitions in both modeling and evaluation. To address these issues, this paper proposes ESOM, an efficient streaming OWVAD model that operates in a training-free manner. ESOM includes a Definition Normalization module to structure user prompts for reducing hallucination, an Inter-frame-matched Intra-frame Token Merging module to compress redundant visual tokens, a Hybrid Streaming Memory module for efficient causal inference, and a Probabilistic Scoring module that converts interval-level textual outputs into frame-level anomaly scores. In addition, this paper introduces OpenDef-Bench, a new benchmark with clean surveillance videos and diverse natural anomaly definitions for evaluating performance under varying conditions. Extensive experiments show that ESOM achieves real-time efficiency on a single GPU and state-of-the-art performance in anomaly temporal localization, classification, and description generation. The code and benchmark will be released at https://github.com/Kamino666/ESOM_OpenDef-Bench.

Huixin Sun, Linlin Yang, Ronyu Chen et al.

Despite significant advances in generic object detection, a persistent performance gap remains for tiny objects compared to normal-scale objects. We demonstrate that tiny objects are highly sensitive to annotation noise, where optimizing strict localization objectives risks noise overfitting. To address this, we propose Tiny Object Localization with Flows (TOLF), a noise-robust localization framework leveraging normalizing flows for flexible error modeling and uncertainty-guided optimization. Our method captures complex, non-Gaussian prediction distributions through flow-based error modeling, enabling robust learning under noisy supervision. An uncertainty-aware gradient modulation mechanism further suppresses learning from high-uncertainty, noise-prone samples, mitigating overfitting while stabilizing training. Extensive experiments across three datasets validate our approach's effectiveness. Especially, TOLF boosts the DINO baseline by 1.2% AP on the AI-TOD dataset.

Gengliang Li, Rongyu Chen, Bin Li et al.

Ensuring factual consistency and reliable reasoning remains a critical challenge for medical vision-language models. We introduce MEDFACT-R1, a two-stage framework that integrates external knowledge grounding with reinforcement learning to improve the factual medical reasoning. The first stage uses pseudo-label supervised fine-tuning (SFT) to incorporate external factual expertise; while the second stage applies Group Relative Policy Optimization (GRPO) with four tailored factual reward signals to encourage self-consistent reasoning. Across three public medical QA benchmarks, MEDFACT-R1 delivers up to 22.5% absolute improvement in factual accuracy over previous state-of-the-art methods. Ablation studies highlight the necessity of pseudo-label SFT cold start and validate the contribution of each GRPO reward, underscoring the synergy between knowledge grounding and RL-driven reasoning for trustworthy medical AI. Codes are released at https://github.com/Garfieldgengliang/MEDFACT-R1.

Qingcheng Zhu, Yangyang Ren, Linlin Yang et al.

Deploying large language models (LLMs) is challenging due to their massive parameters and high computational costs. Ultra low-bit quantization can significantly reduce storage and accelerate inference, but extreme compression (i.e., mean bit-width <= 2) often leads to severe performance degradation. To address this, we propose Squeeze10-LLM, effectively "squeezing" 16-bit LLMs' weights by 10 times. Specifically, Squeeze10-LLM is a staged mixed-precision post-training quantization (PTQ) framework and achieves an average of 1.6 bits per weight by quantizing 80% of the weights to 1 bit and 20% to 4 bits. We introduce Squeeze10LLM with two key innovations: Post-Binarization Activation Robustness (PBAR) and Full Information Activation Supervision (FIAS). PBAR is a refined weight significance metric that accounts for the impact of quantization on activations, improving accuracy in low-bit settings. FIAS is a strategy that preserves full activation information during quantization to mitigate cumulative error propagation across layers. Experiments on LLaMA and LLaMA2 show that Squeeze10-LLM achieves state-of-the-art performance for sub-2bit weight-only quantization, improving average accuracy from 43% to 56% on six zero-shot classification tasks--a significant boost over existing PTQ methods. Our code will be released upon publication.

Zihao Liu, Xiaoyu Wu, Wenna Li et al.

Video Anomaly Detection (VAD), which aims to detect anomalies that deviate from expectation, has attracted increasing attention in recent years. Existing advancements in VAD primarily focus on model architectures and training strategies, while devoting insufficient attention to evaluation metrics and benchmarks. In this paper, we rethink VAD evaluation methods through comprehensive analyses, revealing three critical limitations in current practices: 1) existing metrics are significantly influenced by single annotation bias; 2) current metrics fail to reward early detection of anomalies; 3) available benchmarks lack the capability to evaluate scene overfitting of fully/weakly-supervised algorithms. To address these limitations, we propose three novel evaluation methods: first, we establish probabilistic AUC/AP (Prob-AUC/AP) metrics utlizing multi-round annotations to mitigate single annotation bias; second, we develop a Latency-aware Average Precision (LaAP) metric that rewards early and accurate anomaly detection; and finally, we introduce two hard normal benchmarks (UCF-HN, MSAD-HN) with videos specifically designed to evaluate scene overfitting. We report performance comparisons of ten state-of-the-art VAD approaches using our proposed evaluation methods, providing novel perspectives for future VAD model development. We release our data and code in https://github.com/Kamino666/RethinkingVAD.

Zhuoran Zhao, Linlin Yang, Pengzhan Sun et al.

Recent synthetic 3D human datasets for the face, body, and hands have pushed the limits on photorealism. Face recognition and body pose estimation have achieved state-of-the-art performance using synthetic training data alone, but for the hand, there is still a large synthetic-to-real gap. This paper presents the first systematic study of the synthetic-to-real gap of 3D hand pose estimation. We analyze the gap and identify key components such as the forearm, image frequency statistics, hand pose, and object occlusions. To facilitate our analysis, we propose a data synthesis pipeline to synthesize high-quality data. We demonstrate that synthetic hand data can achieve the same level of accuracy as real data when integrating our identified components, paving the path to use synthetic data alone for hand pose estimation. Code and data are available at: https://github.com/delaprada/HandSynthesis.git.

Haoyu Huang, Boyu Liu, Linlin Yang et al.

The training of Binary Neural Networks (BNNs) is fundamentally based on gradient approximation for non-differentiable binarization operations (e.g., sign function). However, prevailing methods including the Straight-Through Estimator (STE) and its improved variants, rely on hand-crafted designs that suffer from gradient mismatch problem and information loss induced by fixed-range gradient clipping. To address this, we propose SURrogate GradiEnt Adaptation (SURGE), a novel learnable gradient compensation framework with theoretical grounding. SURGE mitigates gradient mismatch through auxiliary backpropagation. Specifically, we design a Dual-Path Gradient Compensator (DPGC) that constructs a parallel full-precision auxiliary branch for each binarized layer, decoupling gradient flow via output decomposition during backpropagation. DPGC enables bias-reduced gradient estimation by leveraging the full-precision branch to estimate components beyond STE's first-order approximation. To further enhance training stability, we introduce an Adaptive Gradient Scaler (AGS) based on an optimal scale factor to dynamically balance inter-branch gradient contributions via norm-based scaling. Experiments on image classification, object detection, and language understanding tasks demonstrate that SURGE performs best over state-of-the-art methods.

Changbai Li, Haodong Zhu, Hanlin Chen et al.

While 3D Gaussian Splatting (3DGS) enables high-quality, real-time rendering for bounded scenes, its extension to large-scale urban environments gives rise to critical challenges in terms of geometric consistency, memory efficiency, and computational scalability. To address these issues, we present UrbanGS, a scalable reconstruction framework that effectively tackles these challenges for city-scale applications. First, we propose a Depth-Consistent D-Normal Regularization module. Unlike existing approaches that rely solely on monocular normal estimators, which can effectively update rotation parameters yet struggle to update position parameters, our method integrates D-Normal constraints with external depth supervision. This allows for comprehensive updates of all geometric parameters. By further incorporating an adaptive confidence weighting mechanism based on gradient consistency and inverse depth deviation, our approach significantly enhances multi-view depth alignment and geometric coherence, which effectively resolves the issue of geometric accuracy in complex large-scale scenes. To improve scalability, we introduce a Spatially Adaptive Gaussian Pruning (SAGP) strategy, which dynamically adjusts Gaussian density based on local geometric complexity and visibility to reduce redundancy. Additionally, a unified partitioning and view assignment scheme is designed to eliminate boundary artifacts and optimize computational load. Extensive experiments on multiple urban datasets demonstrate that UrbanGS achieves superior performance in rendering quality, geometric accuracy, and memory efficiency, providing a systematic solution for high-fidelity large-scale scene reconstruction.

Jiayin Zhu, Linlin Yang, Yicong Li et al.

Optimization-based text-to-3D methods distill guidance from 2D generative models via Score Distillation Sampling (SDS), but implicitly treat this guidance as static. This work shows that ignoring source dynamics yields inconsistent trajectories that suppress or merge semantic cues, leading to "semantic over-smoothing" artifacts. As such, we reformulate text-to-3D optimization as mapping a dynamically evolving source distribution to a fixed target distribution. We cast the problem into a dual-conditioned latent space, conditioned on both the text prompt and the intermediately rendered image. Given this joint setup, we observe that the image condition naturally anchors the current source distribution. Building on this insight, we introduce AnchorDS, an improved score distillation mechanism that provides state-anchored guidance with image conditions and stabilizes generation. We further penalize erroneous source estimates and design a lightweight filter strategy and fine-tuning strategy that refines the anchor with negligible overhead. AnchorDS produces finer-grained detail, more natural colours, and stronger semantic consistency, particularly for complex prompts, while maintaining efficiency. Extensive experiments show that our method surpasses previous methods in both quality and efficiency.

Zicong Fan, Takehiko Ohkawa, Linlin Yang et al.

We interact with the world with our hands and see it through our own (egocentric) perspective. A holistic 3Dunderstanding of such interactions from egocentric views is important for tasks in robotics, AR/VR, action recognition and motion generation. Accurately reconstructing such interactions in 3D is challenging due to heavy occlusion, viewpoint bias, camera distortion, and motion blur from the head movement. To this end, we designed the HANDS23 challenge based on the AssemblyHands and ARCTIC datasets with carefully designed training and testing splits. Based on the results of the top submitted methods and more recent baselines on the leaderboards, we perform a thorough analysis on 3D hand(-object) reconstruction tasks. Our analysis demonstrates the effectiveness of addressing distortion specific to egocentric cameras, adopting high-capacity transformers to learn complex hand-object interactions, and fusing predictions from different views. Our study further reveals challenging scenarios intractable with state-of-the-art methods, such as fast hand motion, object reconstruction from narrow egocentric views, and close contact between two hands and objects. Our efforts will enrich the community's knowledge foundation and facilitate future hand studies on egocentric hand-object interactions.

Jiayin Zhu, Linlin Yang, Angela Yao

We present InstructHumans, a novel framework for instruction-driven {animatable} 3D human texture editing. Existing text-based 3D editing methods often directly apply Score Distillation Sampling (SDS). SDS, designed for generation tasks, cannot account for the defining requirement of editing -- maintaining consistency with the source avatar. This work shows that naively using SDS harms editing, as it may destroy consistency. We propose a modified SDS for Editing (SDS-E) that selectively incorporates subterms of SDS across diffusion timesteps. We further enhance SDS-E with spatial smoothness regularization and gradient-based viewpoint sampling for edits with sharp and high-fidelity detailing. Incorporating SDS-E into a 3D human texture editing framework allows us to outperform existing 3D editing methods. Our avatars faithfully reflect the textual edits while remaining consistent with the original avatars. Project page: https://jyzhu.top/instruct-humans/.

Haodong Zhu, Wenhao Dong, Linlin Yang et al.

Leveraging the complementary characteristics of visible (RGB) and infrared (IR) imagery offers significant potential for improving object detection. In this paper, we propose WaveMamba, a cross-modality fusion method that efficiently integrates the unique and complementary frequency features of RGB and IR decomposed by Discrete Wavelet Transform (DWT). An improved detection head incorporating the Inverse Discrete Wavelet Transform (IDWT) is also proposed to reduce information loss and produce the final detection results. The core of our approach is the introduction of WaveMamba Fusion Block (WMFB), which facilitates comprehensive fusion across low-/high-frequency sub-bands. Within WMFB, the Low-frequency Mamba Fusion Block (LMFB), built upon the Mamba framework, first performs initial low-frequency feature fusion with channel swapping, followed by deep fusion with an advanced gated attention mechanism for enhanced integration. High-frequency features are enhanced using a strategy that applies an ``absolute maximum" fusion approach. These advancements lead to significant performance gains, with our method surpassing state-of-the-art approaches and achieving average mAP improvements of 4.5% on four benchmarks.

Jiaxin Deng, Qingcheng Zhu, Junbiao Pang et al.

Little research explores the correlation between the expressive ability and generalization ability of the low-rank adaptation (LoRA). Sharpness-Aware Minimization (SAM) improves model generalization for both Convolutional Neural Networks (CNNs) and Transformers by encouraging convergence to locally flat minima. However, the connection between sharpness and generalization has not been fully explored for LoRA due to the lack of tools to either empirically seek flat minima or develop theoretical methods. In this work, we propose Flat-LoRA and its efficient version i.e., EFlat-LoRA, to seek flat minima for LoRA. Concretely, we theoretically demonstrate that perturbations in the full parameter space can be transferred to the low-rank subspace. This approach eliminates the potential interference introduced by perturbations across multiple matrices in the low-rank subspace. Our extensive experiments on large language models and vision-language models demonstrate that EFlat-LoRA achieves optimize efficiency comparable to that of LoRA while simultaneously attaining comparable or even better performance. For example, on the GLUE dataset with RoBERTa-large, EFlat-LoRA outperforms LoRA and full fine-tuning by 1.0% and 0.5% on average, respectively. On vision-language models e.g., Qwen-VL-Chat shows performance improvements of 1.5% and 1.0% on SQA and VizWiz datasets, respectively. These empirical results also verify that the generalization of LoRA is closely related to sharpness, which is omitted by previous methods.

Zhiyi Zhu, Xiaoyu Wu, Zihao Liu et al.

Video Temporal Grounding (VTG), which aims to localize video clips corresponding to natural language queries, is a fundamental yet challenging task in video understanding. Existing Transformer-based methods often suffer from redundant attention and suboptimal multi-modal alignment. To address these limitations, we propose MLVTG, a novel framework that integrates two key modules: MambaAligner and LLMRefiner. MambaAligner uses stacked Vision Mamba blocks as a backbone instead of Transformers to model temporal dependencies and extract robust video representations for multi-modal alignment. LLMRefiner leverages the specific frozen layer of a pre-trained Large Language Model (LLM) to implicitly transfer semantic priors, enhancing multi-modal alignment without fine-tuning. This dual alignment strategy, temporal modeling via structured state-space dynamics and semantic purification via textual priors, enables more precise localization. Extensive experiments on QVHighlights, Charades-STA, and TVSum demonstrate that MLVTG achieves state-of-the-art performance and significantly outperforms existing baselines.

Qiuxia Lin, Kerui Gu, Linlin Yang et al.

Online test-time adaptation for 3D human pose estimation is used for video streams that differ from training data. Ground truth 2D poses are used for adaptation, but only estimated 2D poses are available in practice. This paper addresses adapting models to streaming videos with estimated 2D poses. Comparing adaptations reveals the challenge of limiting estimation errors while preserving accurate pose information. To this end, we propose adaptive aggregation, a two-stage optimization, and local augmentation for handling varying levels of estimated pose error. First, we perform adaptive aggregation across videos to initialize the model state with labeled representative samples. Within each video, we use a two-stage optimization to benefit from 2D fitting while minimizing the impact of erroneous updates. Second, we employ local augmentation, using adjacent confident samples to update the model before adapting to the current non-confident sample. Our method surpasses state-of-the-art by a large margin, advancing adaptation towards more practical settings of using estimated 2D poses.

Yuguang Yang, Tongfei Chen, Haoyu Huang et al.

Zero-shot medical detection can further improve detection performance without relying on annotated medical images even upon the fine-tuned model, showing great clinical value. Recent studies leverage grounded vision-language models (GLIP) to achieve this by using detailed disease descriptions as prompts for the target disease name during the inference phase. However, these methods typically treat prompts as equivalent context to the target name, making it difficult to assign specific disease knowledge based on visual information, leading to a coarse alignment between images and target descriptions. In this paper, we propose StructuralGLIP, which introduces an auxiliary branch to encode prompts into a latent knowledge bank layer-by-layer, enabling more context-aware and fine-grained alignment. Specifically, in each layer, we select highly similar features from both the image representation and the knowledge bank, forming structural representations that capture nuanced relationships between image patches and target descriptions. These features are then fused across modalities to further enhance detection performance. Extensive experiments demonstrate that StructuralGLIP achieves a +4.1\% AP improvement over prior state-of-the-art methods across seven zero-shot medical detection benchmarks, and consistently improves fine-tuned models by +3.2\% AP on endoscopy image datasets.

Ziwei Yu, Chen Li, Linlin Yang et al.

Direct mesh fitting for 3D hand shape reconstruction is highly accurate. However, the reconstructed meshes are prone to artifacts and do not appear as plausible hand shapes. Conversely, parametric models like MANO ensure plausible hand shapes but are not as accurate as the non-parametric methods. In this work, we introduce a novel weakly-supervised hand shape estimation framework that integrates non-parametric mesh fitting with MANO model in an end-to-end fashion. Our joint model overcomes the tradeoff in accuracy and plausibility to yield well-aligned and high-quality 3D meshes, especially in challenging two-hand and hand-object interaction scenarios.

Ziwei Yu, Linlin Yang, Shicheng Chen et al.

This paper addresses the 3D point cloud reconstruction and 3D pose estimation of the human hand from a single RGB image. To that end, we present a novel pipeline for local and global point cloud reconstruction using a 3D hand template while learning a latent representation for pose estimation. To demonstrate our method, we introduce a new multi-view hand posture dataset to obtain complete 3D point clouds of the hand in the real world. Experiments on our newly proposed dataset and four public benchmarks demonstrate the model's strengths. Our method outperforms competitors in 3D pose estimation while reconstructing realistic-looking complete 3D hand point clouds.

Hongying Liu, Zhubo Ruan, Peng Zhao et al.

In recent years, deep learning has made great progress in many fields such as image recognition, natural language processing, speech recognition and video super-resolution. In this survey, we comprehensively investigate 33 state-of-the-art video super-resolution (VSR) methods based on deep learning. It is well known that the leverage of information within video frames is important for video super-resolution. Thus we propose a taxonomy and classify the methods into six sub-categories according to the ways of utilizing inter-frame information. Moreover, the architectures and implementation details of all the methods are depicted in detail. Finally, we summarize and compare the performance of the representative VSR method on some benchmark datasets. We also discuss some challenges, which need to be further addressed by researchers in the community of VSR. To the best of our knowledge, this work is the first systematic review on VSR tasks, and it is expected to make a contribution to the development of recent studies in this area and potentially deepen our understanding to the VSR techniques based on deep learning.

Li'an Zhuo, Baochang Zhang, Linlin Yang et al.

Conventional learning methods simplify the bilinear model by regarding two intrinsically coupled factors independently, which degrades the optimization procedure. One reason lies in the insufficient training due to the asynchronous gradient descent, which results in vanishing gradients for the coupled variables. In this paper, we introduce a Cogradient Descent algorithm (CoGD) to address the bilinear problem, based on a theoretical framework to coordinate the gradient of hidden variables via a projection function. We solve one variable by considering its coupling relationship with the other, leading to a synchronous gradient descent to facilitate the optimization procedure. Our algorithm is applied to solve problems with one variable under the sparsity constraint, which is widely used in the learning paradigm. We validate our CoGD considering an extensive set of applications including image reconstruction, inpainting, and network pruning. Experiments show that it improves the state-of-the-art by a significant margin.

Li'an Zhuo, Baochang Zhang, Hanlin Chen et al.

Neural architecture search (NAS) proves to be among the best approaches for many tasks by generating an application-adaptive neural architecture, which is still challenged by high computational cost and memory consumption. At the same time, 1-bit convolutional neural networks (CNNs) with binarized weights and activations show their potential for resource-limited embedded devices. One natural approach is to use 1-bit CNNs to reduce the computation and memory cost of NAS by taking advantage of the strengths of each in a unified framework. To this end, a Child-Parent (CP) model is introduced to a differentiable NAS to search the binarized architecture (Child) under the supervision of a full-precision model (Parent). In the search stage, the Child-Parent model uses an indicator generated by the child and parent model accuracy to evaluate the performance and abandon operations with less potential. In the training stage, a kernel-level CP loss is introduced to optimize the binarized network. Extensive experiments demonstrate that the proposed CP-NAS achieves a comparable accuracy with traditional NAS on both the CIFAR and ImageNet databases. It achieves the accuracy of $95.27\%$ on CIFAR-10, $64.3\%$ on ImageNet with binarized weights and activations, and a $30\%$ faster search than prior arts.

Anil Armagan, Guillermo Garcia-Hernando, Seungryul Baek et al.

We study how well different types of approaches generalise in the task of 3D hand pose estimation under single hand scenarios and hand-object interaction. We show that the accuracy of state-of-the-art methods can drop, and that they fail mostly on poses absent from the training set. Unfortunately, since the space of hand poses is highly dimensional, it is inherently not feasible to cover the whole space densely, despite recent efforts in collecting large-scale training datasets. This sampling problem is even more severe when hands are interacting with objects and/or inputs are RGB rather than depth images, as RGB images also vary with lighting conditions and colors. To address these issues, we designed a public challenge (HANDS'19) to evaluate the abilities of current 3D hand pose estimators (HPEs) to interpolate and extrapolate the poses of a training set. More exactly, HANDS'19 is designed (a) to evaluate the influence of both depth and color modalities on 3D hand pose estimation, under the presence or absence of objects; (b) to assess the generalisation abilities w.r.t. four main axes: shapes, articulations, viewpoints, and objects; (c) to explore the use of a synthetic hand model to fill the gaps of current datasets. Through the challenge, the overall accuracy has dramatically improved over the baseline, especially on extrapolation tasks, from 27mm to 13mm mean joint error. Our analyses highlight the impacts of: Data pre-processing, ensemble approaches, the use of a parametric 3D hand model (MANO), and different HPE methods/backbones.

Linlin Yang, Angela Yao

Hand image synthesis and pose estimation from RGB images are both highly challenging tasks due to the large discrepancy between factors of variation ranging from image background content to camera viewpoint. To better analyze these factors of variation, we propose the use of disentangled representations and a disentangled variational autoencoder (dVAE) that allows for specific sampling and inference of these factors. The derived objective from the variational lower bound as well as the proposed training strategy are highly flexible, allowing us to handle cross-modal encoders and decoders as well as semi-supervised learning scenarios. Experiments show that our dVAE can synthesize highly realistic images of the hand specifiable by both pose and image background content and also estimate 3D hand poses from RGB images with accuracy competitive with state-of-the-art on two public benchmarks.