cs.AI(2025-05-29)
📊 共 8 篇论文 | 🔗 1 篇有代码
🎯 兴趣领域导航
支柱九:具身大模型 (Embodied Foundation Models) (5)
支柱二:RL算法与架构 (RL & Architecture) (2 🔗1)
支柱一:机器人控制 (Robot Control) (1)
🔬 支柱九:具身大模型 (Embodied Foundation Models) (5 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Can Large Language Models Challenge CNNs in Medical Image Analysis? | 多模态AI框架:探索LLM在医学图像分析中挑战CNN的能力 | large language model multimodal | ||
| 2 | mRAG: Elucidating the Design Space of Multi-modal Retrieval-Augmented Generation | mRAG:系统性剖析多模态检索增强生成的设计空间,提升LVLM在现实场景中的性能。 | multimodal visual grounding | ||
| 3 | Evaluating Prompt Engineering Techniques for Accuracy and Confidence Elicitation in Medical LLMs | 评估Prompt工程技术在医学LLM中的准确性和置信度诱导效果 | large language model chain-of-thought | ||
| 4 | Using Reasoning Models to Generate Search Heuristics that Solve Open Instances of Combinatorial Design Problems | 利用推理模型生成搜索启发式算法,解决组合设计开放问题 | large language model | ||
| 5 | Human Empathy as Encoder: AI-Assisted Depression Assessment in Special Education | 提出HEAE框架,融合人类同理心与AI,提升特殊教育中抑郁症评估的准确性。 | multimodal |
🔬 支柱二:RL算法与架构 (RL & Architecture) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 6 | Contextual Integrity in LLMs via Reasoning and Reinforcement Learning | 提出基于推理和强化学习的上下文完整性方法,提升LLM信息披露的安全性。 | reinforcement learning | ✅ | |
| 7 | OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation | 提出OWL框架,通过优化领域无关的规划器,实现多智能体系统在真实世界任务自动化中的跨领域泛化。 | reinforcement learning large language model |
🔬 支柱一:机器人控制 (Robot Control) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 8 | Human sensory-musculoskeletal modeling and control of whole-body movements | 提出SMS-Human模型,结合多模态感知与强化学习,实现全身运动的建模与控制 | bipedal biped locomotion |