cs.CV（2025-08-30）

📊 共 22 篇论文 | 🔗 7 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (9 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (7 🔗3) 支柱六：视频提取与匹配 (Video Extraction) (3) 支柱三：空间感知与语义 (Perception & Semantics) (2 🔗1) 支柱一：机器人控制 (Robot Control) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#题目一句话要点标签🔗⭐
1 A Modality-agnostic Multi-task Foundation Model for Human Brain Imaging 提出BrainFM以解决脑部成像多模态泛化问题 foundation model ✅
2 LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression 提出LightVLM以加速多模态模型推理过程 multimodal
3 Adaptive Point-Prompt Tuning: Fine-Tuning Heterogeneous Foundation Models for 3D Point Cloud Analysis 提出自适应点提示调优方法以解决3D点云分析问题 foundation model
4 A Multimodal and Multi-centric Head and Neck Cancer Dataset for Segmentation, Diagnosis and Outcome Prediction 提出多模态头颈癌数据集以促进肿瘤分割与预后预测 multimodal
5 SurgLLM: A Versatile Large Multimodal Model with Spatial Focus and Temporal Awareness for Surgical Video Understanding 提出SurgLLM以解决外科视频理解中的空间和时间感知不足问题 multimodal ✅
6 TrimTokenator: Towards Adaptive Visual Token Pruning for Large Multimodal Models 提出视觉令牌修剪策略以提升多模态模型的推理效率 multimodal
7 Two Causes, Not One: Rethinking Omission and Fabrication Hallucinations in MLLMs 提出视觉潜力场校准以解决多模态大语言模型的幻觉问题 large language model multimodal
8 A Dataset Generation Scheme Based on Video2EEG-SPGN-Diffusion for SEED-VD 提出Video2EEG-SPGN-Diffusion以生成视频刺激下的EEG数据集 multimodal
9 Activation Steering Meets Preference Optimization: Defense Against Jailbreaks in Vision Language Models 提出SPO-VLM以解决视觉语言模型的对抗攻击问题 visual grounding

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
10 VideoRewardBench: Comprehensive Evaluation of Multimodal Reward Models for Video Understanding 提出VideoRewardBench以解决视频理解中多模态奖励模型评估不足的问题 reinforcement learning multimodal
11 SemaMIL: Semantic-Aware Multiple Instance Learning with Retrieval-Guided State Space Modeling for Whole Slide Images 提出SemaMIL以解决全切片图像中的多实例学习问题 SSM state space model
12 MorphGen: Morphology-Guided Representation Learning for Robust Single-Domain Generalization in Histopathological Cancer Classification 提出MorphGen以解决组织病理学癌症分类中的领域泛化问题 representation learning contrastive learning ✅
13 Make me an Expert: Distilling from Generalist Black-Box Models into Specialized Models for Semantic Segmentation 提出黑箱蒸馏方法以解决局部模型训练问题 distillation open-vocabulary open vocabulary ✅
14 Context-Aware Knowledge Distillation with Adaptive Weighting for Image Classification 提出自适应知识蒸馏框架以优化图像分类性能 distillation
15 LUT-Fuse: Towards Extremely Fast Infrared and Visible Image Fusion via Distillation to Learnable Look-Up Tables 提出LUT-Fuse以解决实时红外与可见光图像融合问题 distillation ✅
16 Multi-Focused Video Group Activities Hashing 提出多聚焦视频组活动哈希技术以解决视频检索问题 representation learning spatiotemporal

🔬 支柱六：视频提取与匹配 (Video Extraction) (3 篇)

#题目一句话要点标签🔗⭐
17 AQFusionNet: Multimodal Deep Learning for Air Quality Index Prediction with Imagery and Sensor Data 提出AQFusionNet以解决资源受限地区空气质量监测问题 sparse sensors multimodal
18 HERO-VQL: Hierarchical, Egocentric and Robust Visual Query Localization 提出HERO-VQL以解决自我中心视频中的视觉查询定位问题 egocentric
19 Learning Yourself: Class-Incremental Semantic Segmentation with Language-Inspired Bootstrapped Disentanglement 提出语言启发的自我学习框架以解决增量语义分割中的灾难性语义纠缠问题 feature matching

🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)

#题目一句话要点标签🔗⭐
20 DGL-RSIS: Decoupling Global Spatial Context and Local Class Semantics for Training-Free Remote Sensing Image Segmentation 提出DGL-RSIS以解决遥感图像分割中的训练需求问题 open-vocabulary open vocabulary multimodal
21 Encoder-Only Image Registration 提出Encoder-Only图像配准框架以解决计算复杂性与大变形问题 optical flow ✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
22 Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation 提出Face-MoGLE以解决可控人脸生成问题 manipulation multimodal ✅

⬅️ 返回 cs.CV 首页 · 🏠 返回主页