cs.CV（2026-06-24）

📊 共 34 篇论文 | 🔗 9 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (15 🔗5) 支柱九：具身大模型 (Embodied Foundation Models) (10 🔗4) 支柱一：机器人控制 (Robot Control) (3) 支柱四：生成式动作 (Generative Motion) (2) 支柱七：动作重定向 (Motion Retargeting) (2) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱五：交互与反应 (Interaction & Reaction) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (15 篇)

#题目一句话要点标签🔗⭐
1 SAC$^2$-Net: Semantic Anchoring and Complementary-Consensus Fusion for Multimodal Micro-Expression Recognition 提出SAC$^2$-Net以解决多模态微表情识别中的异质性问题 SAC contrastive learning optical flow
2 Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models 提出Causal-rCM以解决流媒体视频生成中的自回归扩散蒸馏问题 world model world models distillation
3 Efficient Remote Sensing Instance Segmentation with Linear-Time State Space Distilled Visual Foundation Models 提出RS4D以解决遥感实例分割的计算效率问题 SSM state space model distillation ✅
4 TACO: Towards Task-Consistent Open-Vocabulary Adaptation in Video Recognition 提出TACO框架以解决视频识别中的开放词汇适应问题 distillation open-vocabulary open vocabulary ✅
5 V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning 提出V-Zero以解决细粒度视觉推理中的标签依赖问题 reinforcement learning distillation large language model ✅
6 USS: Unified Spatial-Semantic Prompts for Embodied Visual Tracking with Latent Dynamics Learning 提出统一空间-语义提示以解决模糊目标定位问题 world model world models latent dynamics ✅
7 A welding penetration prediction model for laser welding process based on self-supervised learning using physics-informed neural networks 提出SimPhysNet以解决激光焊接渗透预测问题 contrastive learning penetration
8 Hypergraph Normal World Models for Logical Visual Anomaly Detection 提出超图正常世界模型以解决逻辑视觉异常检测问题 world model world models
9 LinStereo: Linear-Complexity Global Attention for Multi-Scale Iterative Stereo Matching 提出LinStereo以解决多尺度立体匹配中的信息利用不足问题 linear attention monocular depth Depth Anything
10 PRISM: Feed-Forward Single-Image 3D Reconstruction via Geometric Warp-Residual Modeling 提出PRISM框架以解决单图像3D重建问题 distillation 3D reconstruction
11 Teach-to-Reason: Competition-Guided Reasoning with a Self-Improving Teacher 提出Teach-to-Reason框架以提升胸部X光视觉问答的推理能力 reinforcement learning reward design chain-of-thought
12 State Space Models Meet Remote Sensing: A Survey 综述状态空间模型在遥感中的应用与挑战 SSM state space model ✅
13 FeVOS: Foresight Expression Video Object Segmentation 提出Foresight Expression视频目标分割以解决时空推理问题 reinforcement learning chain-of-thought
14 Heterogeneous and Adept Snapshot Distillation for 3D Semantic Segmentation 提出异构与高效快照蒸馏方法以提升3D语义分割性能 distillation
15 What Does the Brain See? Multiview Neural Representations to Demystify the Brain-Visual Alignment 提出统一多视角EEG表示学习框架以解决脑视觉对齐问题 representation learning contrastive learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗⭐
16 TriViewBench: Controlled Complexity Scaling for Multi-View Structural Reasoning in MLLMs 提出TriViewBench以解决多视角结构推理的可扩展性问题 large language model multimodal chain-of-thought
17 Cross-Attention Multimodal Learning for Predicting Response to Neoadjuvant Imatinib in Gastrointestinal Stromal Tumors: A Multicenter Retrospective Study 提出跨注意力多模态学习框架以预测胃肠道间质瘤对伊马替尼的反应 multimodal
18 Beyond Visual Forensics: Auditing Multimodal Robustness for Synthetic Medical Image Detection 提出多模态审计方法以解决合成医学图像检测的脆弱性问题 multimodal ✅
19 LEVIRDet: A Million-Scale 159-Category Dataset and Foundation Model for Universal Remote Sensing Object Detection 提出LEVIRDet数据集与模型以解决遥感目标检测的碎片化问题 foundation model ✅
20 SurgAtlas: A Large-Scale Surgical Video-Language Dataset with 2,391 Hours of Open and Minimally Invasive Surgery 提出SurgAtlas数据集以推动外科视频语言理解研究 foundation model multimodal
21 ShutterMuse: Capture-Time Photography Guidance with MLLMs 提出ShutterMuse以解决摄影时指导不足的问题 large language model multimodal
22 Towards a Dynamic and Fixed-budget Memory Bank for Efficient Streaming Video Understanding 提出CausalMem以解决流媒体视频理解中的记忆管理问题 large language model multimodal ✅
23 SSMNBench: Diagnosing Image-based Cross-View Human-Object Understanding via Single-View Sufficiency and Multi-View Necessity 提出SSMNBench以解决跨视角人机理解的诊断问题 large language model multimodal ✅
24 Falcon: Functional Assembly and Language for Compositional Reasoning in X-ray 提出Falcon以解决X射线行李筛查中的组合威胁推理问题 multimodal
25 Steering Vision-Language Models with Joint Sparse Autoencoders 提出联合稀疏自编码器以提升视觉-语言模型的可控性 multimodal

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#题目一句话要点标签🔗⭐
26 Gastroendoscopy View Synthesis: A New Real Dataset and Evaluation 提出GastroNVS数据集以解决胃镜图像新视角合成问题 manipulation 3D gaussian splatting 3DGS
27 TryOnCrafter: Unleashing Camera Trajectories for Realistic Video Virtual Try-on via a Renderable 4D Try-on Proxy 提出TryOnCrafter以解决视频虚拟试穿中的相机轨迹限制问题 manipulation 3DGS physically plausible
28 Cross-View Variance Correlation in Path-Traced Stereo:A Hidden Shortcut in Synthetic Training Data 揭示路径追踪立体合成数据中的变异性相关性以优化训练 sim-to-real

🔬 支柱四：生成式动作 (Generative Motion) (2 篇)

#题目一句话要点标签🔗⭐
29 A cross-process welding penetration status prediction algorithm based on unsupervised domain adaptation in laser and TIG welding 提出无监督领域适应算法以解决焊接渗透状态预测问题 penetration
30 Follow Your Track: Precise Skeleton Animation Controlled by 3D Trajectories 提出ACT框架以解决4D动画中的运动合成问题 motion synthesis

🔬 支柱七：动作重定向 (Motion Retargeting) (2 篇)

#题目一句话要点标签🔗⭐
31 MVTrack4Gen: Multi-View Point Tracking as Geometric Supervision for 4D Video Generation 提出MVTrack4Gen以解决单目视频生成中的几何一致性问题 geometric consistency
32 Point Cloud Diffusion with Global and Local Reconstruction for Instance-Level 3D Anomaly Detection 提出PCDiff以解决3D点云异常检测中的重建挑战 geometric consistency

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
33 Graph it first! Enabling Reasoning on Long-form Egocentric Videos through Scene Graphs 提出场景图方法以解决长视频理解中的信息损失问题 egocentric large language model

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
34 FedReLa: Imbalanced Federated Learning via Re-Labeling 提出FedReLa以解决联邦学习中的类别不平衡问题 ReMoS

⬅️ 返回 cs.CV 首页 · 🏠 返回主页