cs.CV（2025-05-20）

📊 共 41 篇论文 | 🔗 13 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (16 🔗4) 支柱九：具身大模型 (Embodied Foundation Models) (12 🔗5) 支柱三：空间感知与语义 (Perception & Semantics) (6 🔗4) 支柱一：机器人控制 (Robot Control) (3) 支柱五：交互与反应 (Interaction & Reaction) (1) 支柱四：生成式动作 (Generative Motion) (1) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (16 篇)

#题目一句话要点标签🔗⭐
1 UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning 提出UniVG-R1以解决复杂多模态视觉定位问题 reinforcement learning large language model multimodal ✅
2 UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generation 提出UniGen以解决多模态理解与生成的挑战 direct preference optimization large language model multimodal
3 Visionary-R1: Mitigating Shortcuts in Visual Reasoning with Reinforcement Learning 提出Visionary-R1以解决视觉推理中的快捷学习问题 reinforcement learning large language model multimodal
4 Programmatic Video Prediction Using Large Language Models 提出ProgGen以解决视频帧预测问题 world model large language model
5 Investigating and Enhancing the Robustness of Large Multimodal Models Against Temporal Inconsistency 提出TemRobBench与PanoDPO以解决多模态模型的时间一致性问题 direct preference optimization multimodal
6 VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank 提出VisualQuality-R1以解决图像质量评估中的推理不足问题 reinforcement learning large language model
7 DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning 提出DeepEyes以解决多模态推理中的视觉与文本整合问题 reinforcement learning multimodal ✅
8 Towards Omnidirectional Reasoning with 360-R1: A Dataset, Benchmark, and GRPO-based Method 提出OmniVQA数据集与360-R1方法以解决全景视觉问答问题 reinforcement learning embodied AI large language model
9 StPR: Spatiotemporal Preservation and Routing for Exemplar-Free Video Class-Incremental Learning 提出StPR框架以解决视频类增量学习中的遗忘问题 distillation spatiotemporal
10 Intra-class Patch Swap for Self-Distillation 提出基于类内补丁交换的自蒸馏方法以简化知识蒸馏 teacher-student distillation ✅
11 MultiMAE Meets Earth Observation: Pre-training Multi-modal Multi-task Masked Autoencoders for Earth Observation Tasks 提出MultiMAE以解决多模态地球观测任务的预训练问题 masked autoencoder ✅
12 RETRO: REthinking Tactile Representation Learning with Material PriOrs 提出材料先验以提升触觉表征学习的准确性 representation learning
13 Unify Graph Learning with Text: Unleashing LLM Potentials for Session Search 提出符号图排序器以解决会话搜索中的信息结构建模问题 contrastive learning large language model
14 Scaling Vision Mamba Across Resolutions via Fractal Traversal 提出FractalMamba++以解决视觉输入分辨率适应性问题 Mamba
15 Physics-Driven Local-Whole Elastic Deformation Modeling for Point Cloud Representation Learning 提出物理驱动的局部-整体弹性变形建模以提升点云表示学习 representation learning
16 Ground-V: Teaching VLMs to Ground Complex Instructions in Pixels 提出Ground-V以解决复杂指令的像素级定位问题 distillation instruction following

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#题目一句话要点标签🔗⭐
17 Speculative Decoding Reimagined for Multimodal Large Language Models 提出多模态推测解码以加速多模态大语言模型推理 large language model multimodal ✅
18 EmoSign: A Multimodal Dataset for Understanding Emotions in American Sign Language 提出EmoSign数据集以解决手语情感理解问题 multimodal ✅
19 RAVENEA: A Benchmark for Multimodal Retrieval-Augmented Visual Culture Understanding 提出RAVENEA以解决多模态文化理解不足问题 multimodal
20 Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models 提出视频压缩指挥官以解决视频大语言模型效率问题 large language model ✅
21 ViC-Bench: Benchmarking Visual-Interleaved Chain-of-Thought Capability in MLLMs with Free-Style Intermediate State Representations 提出ViC-Bench以解决现有MLLMs评估中IVS固定问题 chain-of-thought
22 LoVR: A Benchmark for Long Video Retrieval in Multimodal Contexts 提出LoVR基准以解决长视频检索中的多模态挑战 multimodal ✅
23 Scaling and Enhancing LLM-based AVSR: A Sparse Mixture of Projectors Approach 提出Llama-SMoP以解决资源受限环境下的AVSR问题 large language model multimodal
24 RADAR: Enhancing Radiology Report Generation with Supplementary Knowledge Injection 提出RADAR框架以解决放射学报告生成中的知识整合问题 large language model multimodal
25 VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation 提出VideoEval-Pro以解决长视频理解评估的有效性问题 multimodal
26 Unlocking the Power of SAM 2 for Few-Shot Segmentation 提出伪提示生成器与迭代记忆精炼以解决少样本分割问题 foundation model
27 Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting 提出Dolphin以解决文档图像解析中的复杂元素问题 multimodal ✅
28 AppleGrowthVision: A large-scale stereo dataset for phenological analysis, fruit detection, and 3D reconstruction in apple orchards 提出AppleGrowthVision以解决苹果园监测数据集不足问题 multimodal

🔬 支柱三：空间感知与语义 (Perception & Semantics) (6 篇)

#题目一句话要点标签🔗⭐
29 MGStream: Motion-aware 3D Gaussian for Streamable Dynamic Scene Reconstruction 提出MGStream以解决动态场景重建中的闪烁和存储效率问题 3D gaussian splatting 3DGS gaussian splatting ✅
30 M3Depth: Wavelet-Enhanced Depth Estimation on Mars via Mutual Boosting of Dual-Modal Data 提出M3Depth以解决火星环境下深度估计问题 depth estimation stereo depth
31 Personalize Your Gaussian: Consistent 3D Scene Personalization from a Single Image 提出CP-GS框架以解决单图像3D场景个性化问题 3D gaussian splatting 3DGS gaussian splatting ✅
32 Multi-Label Stereo Matching for Transparent Scene Depth Estimation 提出多标签立体匹配方法以解决透明场景深度估计问题 depth estimation scene reconstruction ✅
33 Diving into the Fusion of Monocular Priors for Generalized Stereo Matching 提出二元局部排序图以解决立体匹配中的单目先验融合问题 monocular depth scene flow foundation model
34 4D-ROLLS: 4D Radar Occupancy Learning via LiDAR Supervision 提出4D-ROLLS以解决4D雷达占用估计问题 height map ✅

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#题目一句话要点标签🔗⭐
35 Emerging Properties in Unified Multimodal Pretraining 提出BAGEL模型以解决多模态理解与生成的挑战 manipulation multimodal
36 Vid2World: Crafting Video Diffusion Models to Interactive World Models 提出Vid2World以解决现有世界模型低保真度问题 manipulation world model
37 Visual Agentic Reinforcement Fine-Tuning 提出视觉代理强化微调方法以提升多模态推理能力 manipulation multimodal

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

#题目一句话要点标签🔗⭐
38 Beyond Words: Multimodal LLM Knows When to Speak 提出MM-When2Speak以解决对话中反应时机预测问题 dyadic interaction large language model multimodal

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
39 EGFormer: Towards Efficient and Generalizable Multimodal Semantic Segmentation 提出EGFormer以解决多模态语义分割的效率问题 MDM multimodal

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

#题目一句话要点标签🔗⭐
40 Egocentric Action-aware Inertial Localization in Point Clouds with Vision-Language Guidance 提出以自我中心动作感知的惯性定位框架解决3D点云中的定位漂移问题 egocentric multimodal

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
41 Dynadiff: Single-stage Decoding of Images from Continuously Evolving fMRI 提出Dynadiff以解决动态fMRI图像解码问题 diff-sim

⬅️ 返回 cs.CV 首页 · 🏠 返回主页