YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常

正在读取账号与研究记录…

全站更新概况

+1072新增论文

+845其中 AI 相关

+94已有论文修订

+100新增 AI 导读

arXiv 最近完成扫描：2026-11-10 09:10 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-09 09:30 — 2026-11-10 09:30（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-10 09:10最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

18,172 已收录论文15,506 AI 相关4,527 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 13 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-10 09:09（北京时间）

首次观测 · 记录 #1CVF · CVPR 2026:cvf:059219dbc313741e537708b0d4662d95CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Resolving the Stability-Plasticity Dilemma in Reinforcement Learning via Complementary Continual Critics

Sun, Bo, Peng, Peixi, Tan, Guang, Xu, Haoran, Li, Yaokun, Chang, Yiqian, Wang, Shuaixian, Li, Luntong

原文摘要

This paper proposes the Continual Dual-Critic with Cross-Attention (CD-CCA) framework for visual reinforcement learning to address the plasticity-stability conflict. Our method introduces continual learning techniques into the visual RL architecture, constructing two complementary critics using Continual Backpropagation (CBP) and Elastic Weight Consolidation (EWC) -- one for maintaining representational plasticity for rapid environmental adaptation, and the other for preserving knowledge stability to prevent catastrophic forgetting. Furthermore, we design a cross-attention based fusion mechanism that balances the value estimates from the dual critics according to observation characteristics. Experimental results on DeepMind Control and CARLA benchmarks show that CD-CCA effective mitigates issues of representation drift and policy degradation. Compared to existing visual RL methods, our approach exhibits enhanced robustness and adaptability in non-stationary environments and long-horizon decision-making tasks, providing a new architectural paradigm for the advancement of continual reinforcement learning.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:06647cbe05da91a42d96a855905ae192CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

LaS-Comp: Zero-shot 3D Completion with Latent-Spatial Consistency

Yan, Weilong, Li, Haipeng, Xu, Hao, Ye, Nianjin, Ai, Yihao, Liu, Shuaicheng, Hu, Jingyu

原文摘要

This paper introduces LaS-Comp, a zero-shot and category-agnostic approach that leverages the rich geometric priors of 3D foundation models to enable 3D shape completion across diverse types of partial observations. Our contributions are threefold: First, LaS-Comp harnesses these powerful generative priors for completion through a complementary two-stage design: (i) an explicit replacement stage that preserves the partial observation geometry to ensure faithful completion; and (ii) an implicit refinement stage ensures seamless boundaries between the observed and synthesized regions. Second, our framework is training-free and compatible with different 3D foundation models. Third, we introduce Omni-Comp, a comprehensive benchmark combining real-world and synthetic data with diverse and challenging partial patterns, enabling a more thorough and realistic evaluation. Both quantitative and qualitative experiments demonstrate that our approach outperforms previous state-of-the-art approaches. Code and data will be released upon acceptance.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:229857ebc94b2d59ce3aef93cc62fac7CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

DreamStereo: Towards Real-Time Stereo Inpainting for HD Videos

Huang, Yuan, Zhao, Sijie, Cheng, Jing, Xu, Hao, Jiao, Shaohui

原文摘要

Stereo video inpainting, which aims to fill the occluded regions of warped videos with visually coherent content while maintaining temporal consistency, remains a challenging open problem. The regions to be filled are scattered along object boundaries and occupy only a small fraction of each frame, leading to two key challenges. First, existing approaches perform poorly on such tasks due to the scarcity of high-quality stereo inpainting datasets, which limits their ability to learn effective inpainting priors. Second, these methods apply equal processing to all regions of the frame, even though most pixels require no modification, resulting in substantial redundant computation. To address these issues, we introduce three interconnected components. We first propose Gradient-Aware Parallax Warping (GAPW), which leverages backward warping and the gradient of the coordinate mapping function to obtain continuous edges and smooth occlusion regions. Then, a Parallax-Based Dual Projection (PBDP) strategy is introduced, which incorporates GAPW to produce geometrically consistent stereo inpainting pairs and accurate occlusion masks without requiring stereo videos. Finally, we present Sparsity-Aware Stereo Inpainting (SASI), which reduces over 70% of redundant tokens, achieving a 10.7xspeedup during diffusion inference and delivering results comparable to its full-computation counterpart, enabling real-time processing of HD (768x1280) videos at 25\,FPS on a single A100 GPU.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:2acda52973f0f5dd05e6cca5370079d0CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

BIT: Matching-based Bi-directional Interaction Transformation Network for Visible-Infrared Person Re-Identification

Xu, Haoxuan, Niu, Guanglin

原文摘要

Visible-Infrared Person Re-Identification (VI-ReID) is a challenging retrieval task due to the substantial modality gap between visible and infrared images. While existing methods attempt to bridge this gap by learning modality-invariant features within a shared embedding space, they often overlook the complex and implicit correlations between modalities. This limitation becomes more severe under distribution shifts, where infrared samples are often far fewer than visible ones. To address these challenges, we propose a novel network termed Bi-directional Interaction Transformation (BIT). Instead of relying on rigid feature alignment, BIT adopts a matching-based strategy that explicitly models the interaction between visible and infrared image pairs. Specifically, BIT employs an encoder-decoder architecture where the encoder extracts preliminary feature representations, and the decoder performs bi-directional feature integration and query aware scoring to enhance cross-modality correspondence. To our best knowledge, BIT is the first to introduce such pairwise matching-driven interaction in VI-ReID. Extensive experiments on several benchmarks demonstrate that our BIT achieves state-of-the-art performance, highlighting its effectiveness in the VI-ReID task.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:34dbee9680c8de552385c892d95d471fCVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

MER-Tracker: Towards High-Speed 3D Point Tracking via Multi-View Event-RGB Hybrid Cameras

Chang, Yiqian, Ye, Qinghong, Xu, Haoran, Li, Jianing, Ma, Dongyang, Wang, Xuan, Zhang, Wei, Tian, Yonghong 等 9 位作者

原文摘要

This paper proposes the first task for high-speed 3D point tracking using multi-view Event-RGB hybrid cameras. We design a cuboid observation device comprising 4 RGB cameras (30fps) and 2 Event cameras to synchronously capture high-speed motions, and propose MER-Tracker, a high-frame-rate 3D point-tracking network that fuses the complementary strengths of dual modalities. We first respectively extract 2D motion-change features from the RGB and Event modalities, then apply linear interpolation and anchor sampling to fuse the discrete RGB 3D features and continuous Event 3D features after 3D lifting, and finally employ a LoRA-tuned Transformer based on temporal correlationship to predict the high-frame-rate 3D point trajectories over fast motions, accomplishing high-speed 3D point tracking. To verify the effectiveness of our method, we construct both real-world and simulated high-speed motion datasets. Experiments on these datasets show that our method achieves accurate high-speed 3D point tracking at high-frame-rate (150fps), outperforming state-of-the-art methods.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:876c2fe9f38bf5c8fc52452850d30099CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Towards Policy-Adaptive Image Guardrail: Benchmark and Method

Piao, Caiyong, Yan, Zhiyuan, Xu, Haoming, Zhao, Yunzhen, Lin, Kaiqing, Xu, Feiyang, Zhou, Shuigeng

原文摘要

Accurate rejection of sensitive or harmful visual content, i.e., harmful image guardrail, is critical in many application scenarios. This task must continuously adapt to the evolving safety policies and content across various domains and over time. However, traditional classifiers, confined to fixed categories, require frequent retraining when new policies are introduced. Vision-language models (VLMs) offer a more adaptable and generalizable foundation for dynamic safety guardrails. Despite this potential, existing VLM-based safeguarding methods are typically trained and evaluated under only a fixed safety policy. We find that these models are heavily overfitted to the seen policy, fail to generalize to unseen policies, and even lose the basic instruction-following ability and general knowledge. To address this issue, in this paper we make two key contributions. First, we benchmark the cross-policy generalization performance of existing VLMs with SafeEditBench, a new evaluation suite. SafeEditBench leverages image-editing models to convert unsafe images into safe counterparts, producing policy-aligned datasets where each safe-unsafe image pair remains visually similar except for localized regions violating specific safety rules. Human annotators then provide accurate safe/unsafe labels under five distinct policies, enabling fine-grained assessment of policy-aware generalization. Second, we introduce SafeGuard-VL, a reinforcement learning-based method with verifiable rewards (RLVR) for robust unsafe-image guardrails. Instead of relying solely on supervised fine-tuning (SFT) under fixed policies, SafeGuard-VL explicitly optimizes the model with policy-grounded rewards, promoting verifiable adaptation across evolving policies. Extensive experiments verify the effectiveness of our method for unsafe image guardrails across various policies.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:9b2984d026bdb14e0037a3f3cf379287CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Reinforcing Structured Chain-of-Thought for Video Understanding

Wang, Peiyao, Xu, Haotian, Vesdapunt, Noranart, Hou, Rui, Zhang, Jingyi, Ling, Haibin, Obiednikov, Oleksandr, Zhou, Ning 等 9 位作者

原文摘要

Multi-modal Large Language Models (MLLMs) show promise in video understanding. However, their reasoning often suffers from thinking drift and weak temporal comprehension, even when enhanced by Reinforcement Learning (RL) techniques like Group Relative Policy Optimization (GRPO). Moreover, existing RL methods usually depend on Supervised Fine-Tuning (SFT), which requires costly Chain-of-Thought (CoT) annotation and multi-stage training, and enforces fixed reasoning paths, limiting MLLMs' ability to generalize and potentially inducing bias. To overcome these limitations, we introduce Summary-Driven Reinforcement Learning (SDRL), a novel single-stage RL framework that obviates the need for SFT by utilizing a Structured CoT format: Summarize - Think - Answer. SDRL introduces two self-supervised mechanisms integrated into the GRPO objective: 1) Consistency of Vision Knowledge (CVK) enforces factual grounding by reducing KL divergence among generated summaries; and 2) Dynamic Variety of Reasoning (DVR) promotes exploration by dynamically modulating thinking diversity based on group accuracy. This novel integration effectively balances alignment and exploration, supervising both the final answer and the reasoning process. Our method achieves state-of-the-art performance on seven public VideoQA datasets.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:c035b5bdf8f0da1b7dbe3175570f3b7eCVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

MaskDexGrasp: Generative Masked Modeling for Part-Aware Dexterous Grasp Synthesis

Zuo, Binghui, Zhou, Lin, Xu, Haoxuan, Yan, Jianan, Yu, Zhipeng, Liu, Zekai, Wang, Yangang

原文摘要

Dexterous grasp generation is a predominant task that enables robots to perform human-level manipulation. However, a dexterous hand always maintains high-dimensional DoF and actuation space, making existing approaches that rely on holistic latent representations difficult to produce high-quality and semantically aligned grasps. In this paper, we propose MaskDexGrasp to address these challenges. We first present a part-aware grasp tokenizer that decomposes dexterous grasps into discrete tokens, facilitating compositional modeling of anatomical dependencies. Building upon this representation, a bidirectional masked grasp transformer is then developed to predict grasp tokens conditioned on object geometry and task description, ensuring coherent grasp generation while allowing fine-grained part-level editing. To facilitate evaluation, we construct a dexterous grasp dataset that comprises 65K grasping instances and 260K richly annotated descriptions covering 11 tasks. Comprehensive experiments demonstrate that our method achieves the state-of-the-art performance. Project page is available at https://binghui-z.github.io/MaskDexGrasp/.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:d9a8e947b23e14c2e642225cdab54c4fCVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

EmoTaG: Emotion-Aware Talking Head Synthesis on Gaussian Splatting with Few-Shot Personalization

Xu, Haolan, Cheng, Keli, Wang, Lei, Bi, Ning, Liu, Xiaoming

原文摘要

Audio-driven 3D talking head synthesis has advanced rapidly with Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS). By leveraging rich pre-trained priors, few-shot methods enable instant personalization from just a few seconds of video. However, under expressive facial motion, existing few-shot approaches often suffer from geometric instability and audio-emotion mismatch, highlighting the need for more effective emotion-aware motion modeling. In this work, we present EmoTaG, a few-shot emotion-aware 3D talking head synthesis framework built on the Pretrain-and-Adapt paradigm. Our key insight is to reformulate motion prediction in a structured FLAME parameter space rather than directly deforming 3D Gaussians, thereby introducing explicit geometric priors that improve motion stability. Building upon this, we propose a Gated Residual Motion Network (GRMN), which captures emotional prosody from audio while supplementing head pose and upper-face cues absent from audio, enabling expressive and coherent motion generation. Extensive experiments demonstrate that EmoTaG achieves state-of-the-art performance in emotional expressiveness, lip synchronization, visual realism, and motion stability.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:e71f653bef5ad5596ad758fa255ee592CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

UniFusion: A Unified Image Fusion Framework with Robust Representation and Source-Aware Preservation

Li, Xingyuan, Du, Songcheng, Zou, Yang, Xu, Haoyuan, Jiang, Zhiying, Liu, Jinyuan

原文摘要

Image fusion aims to integrate complementary information from multiple source images to produce a more informative and visually consistent representation, benefiting both human perception and downstream vision tasks. Despite recent progress, most existing fusion methods are designed for specific tasks (i.e., multi-modal, multi-exposure, or multi-focus fusion) and struggle to effectively preserve source information during the fusion process. This limitation primarily arises from task-specific architectures and the degradation of source information caused by deep-layer propagation. To overcome these issues, we propose UniFusion, a unified image fusion framework designed to achieve cross-task generalization. First, leveraging DINOv3 for modality-consistent feature extraction, UniFusion establishes a shared semantic space for diverse inputs. Second, to preserve the understanding of each source image, we introduce a reconstruction-alignment loss to maintain consistency between fused outputs and inputs. Finally, we employ a bilevel optimization strategy to decouple and jointly optimize reconstruction and fusion objectives, effectively balancing their coupling relationship and ensuring smooth convergence. Extensive experiments across multiple fusion tasks demonstrate UniFusion's superior visual quality, generalization ability, and adaptability to real-world scenarios.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:e97adaec4faf34d0522533add1652f08CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

LESA: Learnable Stage-Aware Predictors for Diffusion Model Acceleration

Cai, Peiliang, Liu, Jiacheng, Xu, Haowen, Wang, Xinyu, Zou, Chang, Zhang, Linfeng

原文摘要

Diffusion models have achieved remarkable success in image and video generation tasks. However, the high computational demands of Diffusion Transformers (DiTs) pose a significant challenge to their practical deployment. While feature caching is a promising acceleration strategy, existing methods based on simple reusing or training-free forecasting struggle to adapt to the complex, stage-dependent dynamics of the diffusion process, often resulting in quality degradation and failing to maintain consistency with the standard denoising process. To address this, we propose a LEarnable Stage-Aware (LESA) predictor framework based on two-stage training. Our approach leverages a Kolmogorov-Arnold Network (KAN) to accurately learn temporal feature mappings from data. We further introduce a multi-stage, multi-expert architecture that assigns specialized predictors to different noise-level stages, enabling more precise and robust feature forecasting. Extensive experiments show our method achieves significant acceleration while maintaining high-fidelity generation. Experiments demonstrate 5.00xacceleration on FLUX.1-dev with minimal quality degradation (1.0% drop), 6.25xspeedup on Qwen-Image with a 20.2% quality improvement over the previous SOTA (TaylorSeer), and 5.00xacceleration on HunyuanVideo with a 24.7% PSNR improvement over TaylorSeer. State-of-the-art performance on both text-to-image and text-to-video synthesis validates the effectiveness and generalization capability of our training-based framework across different models. Our code is included in the supplementary materials and will be released on GitHub.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f13cbca8908bd378073c07f5ce57ed2bCVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Bridging Human Evaluation to Infrared and Visible Image Fusion

Liu, Jinyuan, Li, Xingyuan, Mei, Qingyun, Xu, Haoyuan, Jiang, Zhiying, Ma, Long, Liu, Risheng, Fan, Xin

原文摘要

Infrared and visible image fusion (IVIF) integrates complementary modalities to enhance scene perception. Current methods predominantly focus on optimizing handcrafted losses and objective metrics, often resulting in fusion outcomes that do not align with human visual preferences. This challenge is further exacerbated by the ill-posed nature of IVIF, which severely limits its effectiveness in human perceptual environments such as security surveillance and driver assistance systems. To address these limitations, we propose a feedback reinforcement framework that bridges human evaluation to infrared and visible image fusion. To address the lack of human-centric evaluation metrics and data, we introduce the first large-scale human feedback dataset for IVIF, containing multidimensional subjective scores and artifact annotations, and enriched by a fine-tuned large language model with expert review. Based on this dataset, we design a domain-specific reward function and train a reward model to quantify perceptual quality. Guided by this reward, we fine-tune the fusion network through Group Relative Policy Optimization, achieving state-of-the-art performance that better aligns fused images with human aesthetics. Code is available at https://github.com/ALKA-Wind/EVAFusion.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:fce10c03bc2ebd5149d76523f8bc8d02CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

PC-Talk: Precise Facial Animation Control for Audio-Driven Talking Face Generation

Wang, Baiqin, Zhu, Xiangyu, Shen, Fan, Xu, Hao, Lei, Zhen

原文摘要

Recent advancements in audio-driven talking face generation have made great progress in lip synchronization. However, current methods often lack sufficient control over talking face, such as speaking style and emotional expression, resulting in uniform facial motion. In this paper, we focus on improving two key factors: lip-audio alignment control(LAC) and emotion control(EMC), to enhance the diversity and user-friendliness of talking videos. Lip-audio alignment control ensures accurate lip-sync across Recent advancements in audio-driven talking face generation have made great progress in lip synchronization. However, current methods often lack sufficient control over talking face, such as speaking style and emotional expression, resulting in uniform facial motion. In this paper, we focus on improving two key factors: lip-audio alignment control(LAC) and emotion control(EMC), to enhance the diversity and user-friendliness of talking videos. Lip-audio alignment control ensures accurate lip-sync across varied speaking styles to simulate different talking habits, whereas emotion control aims to generate realistic emotional expressions with varying intensities and mixed emotional states. To achieve precise facial animation control, we propose a novel and efficient framework, PC-Talk, which enables lip-audio alignment and emotion control through implicit keypoint deformations. First, our LAC module generates lip-synced talking faces with a specific speaking style, derived from either a video reference or preset options. It also supports lip movement scale adjustment and fine-grained editing of speaking styles for specific articulations. Second, our EMC module produces vivid emotional facial expressions through pure emotional deformation. It further enables precise control over emotion intensity and the compound emotions across different facial regions. Our method demonstrates outstanding control capabilities and achieves SOTA performance on HDTF and MEAD datasets in experiments. Project page: https://bq-wang0511.github.io/PC-Talk/

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文

CVF · CVPR 2026 ↗PDF ↗