cs.AI（2026-06-15）

📊 共 32 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (21 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (10 🔗2) 支柱七：动作重定向 (Motion Retargeting) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (21 篇)

#题目一句话要点标签🔗⭐
1 Latent Thought Flow: Efficient Latent Reasoning in Large Language Models 提出Latent Thought Flow以解决大语言模型推理效率问题 large language model chain-of-thought
2 Consensus-based Agentic Large Language Model Framework for Harmonized Tariff Schedule Code Classification 提出基于共识的智能大型语言模型框架以解决关税编码分类问题 large language model ✅
3 MuVAP: Multimodal Multiparty Voice Activity Projection for Turn-taking Prediction in the Wild 提出MuVAP以解决多方语音活动预测问题 multimodal
4 SpecAlign: Efficient Specification-Grounded Alignment of Large Language Models via Synthetic Data 提出SpecAlign以解决大语言模型对齐问题 large language model
5 AgentFairBench: Do LLM Agents Discriminate When They Act? 提出AgentFairBench以评估LLM代理的公平性问题 large language model chain-of-thought
6 PAL-Bench: Evidence-Grounded Profile Reconstruction from Longitudinal Personal Albums 提出PAL-Bench以解决个人相册的证据基础重建问题 multimodal TAMP
7 Whose hotel does the AI recommend? An algorithm audit of reputation signals in LLM-assisted hotel selection 通过算法审计揭示LLM辅助酒店选择中的声誉信号影响 large language model
8 RAID: Semantic Graph Diffusion for True Cold-Start and Cross-Lingual Forecasting 提出RAID框架以解决真实冷启动和跨语言预测问题 foundation model
9 LabOSBench: Benchmarking Computer Use Agents for Scientific Instrument Control 提出LabOSBench以解决科学仪器控制的基准测试问题 multimodal
10 Optimising Temporary Accommodation Placement Across London with AI-Powered SaaS in E-Governance Systems 提出DOMUS系统以优化伦敦临时住宿分配问题 large language model
11 Using AI in engineering education: a balancing act, driven by clear purpose 探讨AI在工程教育中的应用与挑战 large language model
12 Post-Hoc Merging is Not Enough: Many-Shot Model Merging with Loss-Gap Balancing 提出METIS以解决多任务模型合并中的信息丢失问题 large language model ✅
13 Steering Emotional Dynamics for Art Therapy: Controllable Narrative Script Generation through Hierarchically Guided LLM Agents 提出EC-Script以解决情感动态控制问题 large language model
14 Tensor-Coord: Algebraic Decomposition of Joint Plan Tensors for Conflict-Free Multi-Agent LLM Planning 提出Tensor-Coord以解决多智能体规划中的协调冲突问题 large language model
15 The Proxy Knows Too Much: Sealing LLM API Routers with Attested TEEs 提出AEGIS以解决API路由器安全问题 large language model
16 AdaSTORM: Scaling LLM Reasoning on Dynamic Graphs via Adaptive Spatio-Temporal Multi-Agent Collaboration 提出AdaSTORM以解决动态图推理的扩展瓶颈问题 large language model ✅
17 UXBench: Measuring the Actionability of LLM-Generated UX Critiques 提出UXBench以评估LLM生成的用户体验批评的可操作性 large language model
18 SPARK: Security Knowledge Priming and Representation-Guided Knowledge Activation for LLM-based Secure Code Generation 提出SPARK以解决大语言模型安全代码生成问题 large language model
19 Measuring Whether LLM Tutors Teach or Solve: A Diagnostic for Educational Impact 提出轻量级诊断方法以评估大型语言模型的教育影响 large language model
20 TimeVista: Exploring and Exploiting Vision-Language Models as Judges for Time Series Forecasting 提出TimeVista以解决时间序列预测评估问题 foundation model
21 Know Your Limits : On the Faithfulness of LLMs as Solvers and Autoformalizers in Legal Reasoning 探讨大型语言模型在法律推理中的局限性及信度问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (10 篇)

#题目一句话要点标签🔗⭐
22 Kairos: A Native World Model Stack for Physical AI 提出Kairos以构建物理AI的原生世界模型 world model world models linear attention
23 Medical world models: representing medical states, modelling clinical dynamics and guiding intervention policies 提出医疗世界模型以解决动态医疗决策问题 reinforcement learning world model world models ✅
24 ARB4WM: An Adversarial Robustness Benchmark for World Models in Continuous Control 提出ARB4WM以评估世界模型在连续控制中的对抗鲁棒性 world model world models dreamer ✅
25 OpenClaw-Skill: Collective Skill Tree Search for Agentic Large Language Models 提出Collective Skill Tree Search以增强大型语言模型的技能 reinforcement learning large language model
26 Thinking with Visual Grounding 提出视觉基础思维以解决视觉语言模型的推理可验证性问题 reinforcement learning visual grounding
27 ArtNet: A JEPA-Like Articulatory Predictive Framework for Robust Zero-Shot Phoneme Recognition 提出ArtNet框架以解决零样本跨语言音素识别问题 JEPA Joint-Embedding Predictive Architecture joint-embedding predictive architecture
28 Sensor-Conditioned Representation Learning via Scene-Relevant Observation Quotients 提出传感器条件下的表示学习方法以解决场景区分问题 representation learning contrastive learning
29 ROSA-RL: Uncertainty-Aware Roundabout Optimized Speed Advisory with Reinforcement Learning 提出ROSA-RL以解决环形交叉口不确定性问题 reinforcement learning
30 When in Doubt, Plan It Out: Committed Small Language Model Deliberation for Reactive Reinforcement Learning 提出PACT框架以解决强化学习在陌生环境中的决策问题 reinforcement learning
31 VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models 提出VibeThinker-3B以推动小型语言模型的可验证推理能力 reinforcement learning distillation

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

#题目一句话要点标签🔗⭐
32 TuneJury: An Open Metric for Improving Music Generation Preference Alignment 提出TuneJury以改善音乐生成的偏好对齐问题 latent optimization ✅

⬅️ 返回 cs.AI 首页 · 🏠 返回主页