cs.AI（2025-08-18）

📊 共 24 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (15 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱五：交互与反应 (Interaction & Reaction) (1) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱四：生成式动作 (Generative Motion) (1 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (15 篇)

#题目一句话要点标签🔗⭐
1 E3RG: Building Explicit Emotion-driven Empathetic Response Generation System with Multimodal Large Language Model 提出E3RG以解决多模态情感驱动的同理心响应生成问题 large language model multimodal ✅
2 SPANER: Shared Prompt Aligner for Multimodal Semantic Representation 提出SPANER以解决多模态语义表示的孤立问题 multimodal
3 Towards Unified Multimodal Financial Forecasting: Integrating Sentiment Embeddings and Market Indicators via Cross-Modal Attention 提出STONK框架以解决多模态金融预测问题 multimodal
4 A Language-Signal-Vision Multimodal Framework for Multitask Cardiac Analysis 提出TGMM框架以解决多模态心脏分析问题 multimodal
5 ViTAD: Timing Violation-Aware Debugging of RTL Code using Large Language Models 提出ViTAD以解决RTL代码中的时序违规调试问题 large language model
6 Do Large Language Model Agents Exhibit a Survival Instinct? An Empirical Study in a Sugarscape-Style Simulation 研究大型语言模型代理的生存本能以提升AI安全性 large language model
7 "DIVE" into Hydrogen Storage Materials Discovery with AI Agents 提出DIVE以解决氢储存材料发现中的数据提取问题 large language model multimodal
8 AI Agents for Photonic Integrated Circuit Design Automation 提出PhIDO框架以实现光子集成电路设计自动化 large language model
9 VerilogLAVD: LLM-Aided Rule Generation for Vulnerability Detection in Verilog 提出VerilogLAVD以解决Verilog硬件漏洞检测问题 large language model
10 Using AI for User Representation: An Analysis of 83 Persona Prompts 分析83个用户角色提示以优化AI用户表示 large language model
11 EvolMathEval: Towards Evolvable Benchmarks for Mathematical Reasoning via Evolutionary Testing 提出EvolMathEval以解决数学推理基准评估的挑战 large language model
12 AI-Powered Assistant for Long-Term Access to RHIC Knowledge 提出AI助手以实现RHIC知识的长期访问与保存 large language model
13 SecFSM: Knowledge Graph-Guided Verilog Code Generation for Secure Finite State Machines in Systems-on-Chip 提出SecFSM以解决安全敏感FSM的Verilog代码生成问题 large language model
14 Involuntary Jailbreak 揭示大型语言模型的新型脆弱性：非自愿越狱 large language model
15 An LLM + ASP Workflow for Joint Entity-Relation Extraction 提出LLM与ASP结合的工作流程以解决联合实体关系抽取问题 large language model

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

#题目一句话要点标签🔗⭐
16 Reinforcement Learning with Rubric Anchors 提出基于评分标准的强化学习以解决开放任务的评估问题 reinforcement learning large language model
17 Towards Open-Ended Emotional Support Conversations in LLMs via Reinforcement Learning with Future-Oriented Rewards 提出RLFF-ESC框架以解决情感支持对话系统的灵活性问题 reinforcement learning large language model
18 OPTIC-ER: A Reinforcement Learning Framework for Real-Time Emergency Response and Equitable Resource Allocation in Underserved African Communities 提出OPTIC-ER框架以解决非洲社区紧急响应与资源分配不均问题 reinforcement learning
19 G$^2$RPO-A: Guided Group Relative Policy Optimization with Adaptive Guidance 提出G$^2$RPO-A以解决小型语言模型推理能力不足的问题 reinforcement learning large language model ✅

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

#题目一句话要点标签🔗⭐
20 EGOILLUSION: Benchmarking Hallucinations in Egocentric Video Understanding 提出EgoIllusion以评估自我中心视频理解中的幻觉问题 egocentric large language model multimodal

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

#题目一句话要点标签🔗⭐
21 CardAIc-Agents: A Multimodal Framework with Hierarchical Adaptation for Cardiac Care Support 提出CardAIc-Agents以解决心脏护理支持中的适应性不足问题 ReMoS multimodal

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
22 LOOP: A Plug-and-Play Neuro-Symbolic Framework for Enhancing Planning in Autonomous Systems 提出LOOP框架以解决自主系统规划中的神经符号问题 spatial relationship

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
23 PC-Sampler: Position-Aware Calibration of Decoding Bias in Masked Diffusion Models 提出PC-Sampler以解决MDMs解码策略的局限性 MDM ✅

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
24 XR-NPE: High-Throughput Mixed-precision SIMD Neural Processing Engine for Extended Reality Perception Workloads 提出XR-NPE以解决扩展现实感知工作负载的高效计算问题 VIO ✅

⬅️ 返回 cs.AI 首页 · 🏠 返回主页