cs.AI（2025-12-19）
📊 共 11 篇论文
🎯 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) (4)
支柱一：机器人控制 (Robot Control) (2)
🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Towards Explainable Conversational AI for Early Diagnosis with Large Language Models | 提出基于LLM的对话式AI，用于早期诊断并提升可解释性 | large language model chain-of-thought | ||
| 2 | SWE-Bench++: A Framework for the Scalable Generation of Software Engineering Benchmarks from Open-Source Repositories | SWE-Bench++：一个从开源仓库大规模生成软件工程基准的框架 | large language model | ||
| 3 | LLM-based Behaviour Driven Development for Hardware Design | 提出基于LLM的硬件设计行为驱动开发方法，提升测试验证效率 | large language model | ||
| 4 | UmniBench: Unified Understand and Generation Model Oriented Omni-dimensional Benchmark | 提出 UmniBench，用于统一多模态模型在理解、生成和编辑能力上的全面评估。 | multimodal | ||
| 5 | PILAR: Personalizing Augmented Reality Interactions with LLM-based Human-Centric and Trustworthy Explanations for Daily Use Cases | PILAR：利用LLM生成以人为本的可信解释，个性化增强现实交互，应用于日常场景。 | 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 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 6 | Large Language Models as Pokémon Battle Agents: Strategic Play and Content Generation | 利用大型语言模型作为宝可梦对战智能体，实现策略博弈与内容生成 | reinforcement learning large language model | ||
| 7 | MMRAG-RFT: Two-stage Reinforcement Fine-tuning for Explainable Multi-modal Retrieval-augmented Generation | 提出MMRAG-RFT，通过两阶段强化学习提升多模态检索增强生成的可解释性。 | reinforcement learning large language model multimodal | ||
| 8 | AlignDP: Hybrid Differential Privacy with Rarity-Aware Protection for LLMs | AlignDP：针对LLM的混合差分隐私方法，通过稀有感知保护提升安全性 | distillation large language model | ||
| 9 | About Time: Model-free Reinforcement Learning with Timed Reward Machines | 提出基于时序奖励机的免模型强化学习方法，解决时序约束下的奖励建模问题。 | reinforcement learning |
🔬 支柱一：机器人控制 (Robot Control) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 10 | HydroGym: A Reinforcement Learning Platform for Fluid Dynamics | HydroGym：用于流体动力学的强化学习平台，提供可扩展的控制基准。 | manipulation reinforcement learning | ||
| 11 | Accelerating Multi-modal LLM Gaming Performance via Input Prediction and Mishit Correction | 提出基于输入预测和误差校正的多模态LLM游戏加速框架 | humanoid MPC world model |