cs.CV（2025-08-29）

📊 共 19 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (12 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (2) 支柱五：交互与反应 (Interaction & Reaction) (1)

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

#题目一句话要点标签🔗⭐
1 Multimodal Deep Learning for Phyllodes Tumor Classification from Ultrasound and Clinical Data 提出多模态深度学习框架以提高腺瘤分类准确性 multimodal
2 Foundation Model-Driven Classification of Atypical Mitotic Figures with Domain-Aware Training Strategies 提出基于基础模型的分类方法以解决非典型有丝分裂图像识别问题 foundation model
3 From Drone Imagery to Livability Mapping: AI-powered Environment Perception in Rural China 提出视觉-语言对比排名框架以解决农村环境感知问题 large language model multimodal chain-of-thought
4 MM-SeR: Multimodal Self-Refinement for Lightweight Image Captioning 提出MM-SeR以解决轻量级图像描述的可靠性问题 multimodal
5 Safe-LLaVA: A Privacy-Preserving Vision-Language Dataset and Benchmark for Biometric Safety 提出Safe-LLaVA以解决多模态大语言模型的生物特征泄露问题 large language model multimodal
6 DriveQA: Passing the Driving Knowledge Test 提出DriveQA以解决驾驶知识测试的挑战 large language model multimodal
7 Integrating Pathology and CT Imaging for Personalized Recurrence Risk Prediction in Renal Cancer 提出多模态融合方法以提升肾癌复发风险预测精度 foundation model multimodal
8 Generative AI for Industrial Contour Detection: A Language-Guided Vision System 提出语言引导的生成视觉系统以解决工业轮廓检测问题 multimodal
9 Waste-Bench: A Comprehensive Benchmark for Evaluating VLLMs in Cluttered Environments 提出Waste-Bench以解决复杂环境下VLLMs评估问题 large language model
10 Domain Generalization in-the-Wild: Disentangling Classification from Domain-Aware Representations 提出CLIP-DCA以解决领域泛化评估中的挑战 foundation model
11 Why Stop at Words? Unveiling the Bigger Picture through Line-Level OCR 提出行级OCR以解决词级OCR的局限性 large language model ✅
12 How Well Do Vision--Language Models Understand Cities? A Comparative Study on Spatial Reasoning from Street-View Images 提出城市空间推理新挑战以提升视觉语言模型性能 chain-of-thought

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
13 ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding 提出ELV-Halluc以解决长视频理解中的语义聚合幻觉问题 DPO large language model multimodal
14 Beyond Pixels: Introducing Geometric-Semantic World Priors for Video-based Embodied Models via Spatio-temporal Alignment 提出VEME以解决动态环境中的推理与规划问题 world model scene understanding VLN
15 What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos 提出利用非典型视频提升开放世界学习的视觉表示能力 representation learning ✅
16 UItron: Foundational GUI Agent with Advanced Perception and Planning 提出UItron以解决GUI代理自动化操作问题 reinforcement learning foundation model

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

#题目一句话要点标签🔗⭐
17 Scale-GS: Efficient Scalable Gaussian Splatting via Redundancy-filtering Training on Streaming Content 提出可扩展高效的高斯点云渲染框架以解决动态场景训练问题 3D gaussian splatting 3DGS gaussian splatting
18 Complete Gaussian Splats from a Single Image with Denoising Diffusion Models 提出基于潜在扩散模型的单图像完整高斯点云重建方法 gaussian splatting splatting

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

#题目一句话要点标签🔗⭐
19 ECHO: Ego-Centric modeling of Human-Object interactions 提出ECHO以解决人机交互建模的挑战 human-object interaction HOI egocentric

⬅️ 返回 cs.CV 首页 · 🏠 返回主页