cs.AI（2026-06-05）

📊 共 18 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) (12 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱一：机器人控制 (Robot Control) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

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

#题目一句话要点标签🔗⭐
1 Evidence-Based Intelligent Diagnostic and Therapeutic Visualization System with Large Language Models: Multi-Turn Interaction and Multimodal Treatment Plan Generation 提出知识增强的可视化诊断系统以解决中医诊断透明性不足问题 large language model multimodal
2 DataEvolver: Automatic Data Preparation for Large Language Models through Multi-Level Self-Evolving 提出DataEvolver以解决大语言模型数据准备问题 large language model
3 Quantum-Inspired Trace-Augmented Evidence Selection for Reasoning over Structured Hypothesis Spaces 提出量子启发的证据选择方法以提升法律推理准确性 large language model chain-of-thought
4 Online Pandora's Box for Contextual LLM Cascading 提出在线上下文潘多拉盒子模型以优化LLM API选择 large language model
5 Act As a Real Researcher: A Suite of Benchmarks Evaluating Frontier LLMs and Agentic Harnesses in Research Lifecycle 提出AARR基准以评估前沿LLM在研究生命周期中的表现 foundation model ✅
6 Hierarchical Certified Semantic Commitment for Byzantine-Resilient LLM-Agent Collaboration 提出分层认证语义承诺以解决拜占庭鲁棒性问题 large language model
7 Think Fast: Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models 提出无思维链推理时间估计方法以监控前沿AI模型 chain-of-thought
8 Beyond Post-hoc Explanation: Toward Glassbox AI via Probabilistic Mediation 提出玻璃盒框架以解决AI透明性不足问题 large language model
9 SpectCount: Spectrotemporal Counting via Synthetic Signals Improves Large Audio Language Models 提出SpectCount以解决音频语言模型数据稀缺问题 large language model
10 Workflow-to-Skill: Skill Creation via Routing-Workflow-Semantics-Attachments Decomposition 提出RWSA框架以自动化技能构建解决现有方法不足问题 large language model
11 AdMem: Advanced Memory for Task-solving Agents 提出AdMem框架以解决长任务记忆与知识重用问题 large language model
12 What Your Posts Reveal: A Benchmark and Agentic Framework for User-Level Privacy Leakage on Social Media 提出SopriBench和Argus框架以解决社交媒体用户隐私泄露问题 multimodal

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

#题目一句话要点标签🔗⭐
13 Teaching the Way, Not the Answer: Privileged Tutoring Distillation for Multimodal Policy Optimization 提出PTD-PO框架以解决多模态策略优化中的稀疏奖励问题 reinforcement learning distillation multimodal
14 Exploring Agentic Tool-Calling Decisions via Uncertainty-Aligned Reinforcement Learning 提出TRUST以解决LLM代理工具调用决策不确定性问题 reinforcement learning reward design large language model
15 dots.tts Technical Report 提出dots.tts以解决多语言文本到语音生成的挑战 flow matching distillation foundation model
16 Towards Unified Song Generation and Singing Voice Conversion with Accompaniment Co-Generation 提出UniSinger以解决歌曲生成与歌声转换的协同问题 curriculum learning multimodal

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
17 The Sim-to-Real Gap of Foundation Model Agents: A Unified MDP Perspective 提出统一MDP视角以解决基础模型智能体的仿真与现实差距问题 sim-to-real domain randomization foundation model

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

#题目一句话要点标签🔗⭐
18 Hierarchical Semantic-Constrained Heterogeneous Graph for Audio-Visual Event Localization 提出分层语义约束异构图以解决音视频事件定位问题 open-vocabulary open vocabulary

⬅️ 返回 cs.AI 首页 · 🏠 返回主页