cs.AI（2026-08-31）

📊 共 28 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) (20) 支柱二：RL算法与架构 (RL & Architecture) (7 🔗1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (20 篇)

#题目一句话要点标签🔗⭐
1 CM2: Multimodal Cultural Reasoning via an Integrated Multi-Agent Framework 提出CM2框架以解决多模态文化推理问题 large language model multimodal
2 GarmentWeaver: Schema-Aware Structured Synthesis for Multimodal Sewing Patterns 提出GarmentWeaver以解决多模态缝纫图案生成问题 multimodal
3 Cross-Regional Grapevine Cold Hardiness Prediction via Learned Multimodal Latent Representations 提出跨区域葡萄藤耐寒性预测框架以解决数据稀缺问题 multimodal
4 TuringLLM: Efficiently Scaling Foundation Models Toward Physical AI 提出Turing-20B-A2B以提升物理AI应用的效率与性能 foundation model
5 Dense Clinical Contrasts Enhance Medical Knowledge Updating in Large Language Models 提出SEER-Bench以增强大语言模型的医学知识更新能力 large language model
6 VIBE: Video Instruction-aligned Background music gEneration 提出VIBE以解决视频到音乐生成中的语义控制问题 multimodal instruction following
7 MNIST-PRO: MNIST is Back as a Partially Observable World for AI Agents 提出MNIST-PRO以解决部分可观察环境中的感知问题 multimodal
8 Autoregressive Mosaics: Probing 2D Spatial Reasoning in Text-Only Language Models 提出自回归马赛克基准以探测文本模型的二维空间推理能力 large language model
9 Automated Testing of LLM-Based Post Hoc Explainers Using Model Checking as an Oracle 提出基于模型检查的自动化测试方法以验证LLM生成的解释 large language model
10 Wrong Prediction, Right Answer: Recovering Evidence from Collapsed LLM Sequence Scores 提出一种新方法以恢复大语言模型的推理能力 large language model
11 HSRM: Hidden-State Reward Models for Test-Time Verification 提出HSRM以解决大型语言模型验证效率问题 large language model
12 On the Prospects of Dynamic LLM Conversations in Software Development 通过动态干预提升开发者与LLM的交互质量 large language model
13 ATLAS: Dual-Horizon Diagnostic Evaluation for Industrial Tool-Use Agents 提出ATLAS框架以解决工业工具使用代理的评估问题 large language model
14 Generative Retrieval for E-commerce: Jointly Learning Embedding and Codebook with Same Product Cluster 提出联合学习嵌入与码本以解决电商检索精度问题 large language model
15 Designing an Auditable LLM-Supported Workflow for Qualitative Thematic Analysis 提出可审计的LLM支持定性主题分析工作流程 large language model
16 Towards Cognitive Process-Aware Proactive Writing Support 提出基于认知过程的主动写作支持以解决创作负担问题 large language model
17 DERELAB: Probing Defeasible Reasoning and Confirmation Bias in LLMs with a Generative Benchmark 提出DeReLab框架以研究大型语言模型中的可撤销推理与确认偏差 large language model
18 Augmenting Human Performance with an XR Agent Learning from Online Behavior and BCI Evidence 提出OLIVE框架以增强高压动态任务中的人类表现 foundation model
19 Beyond Ranking Accuracy: Evaluating LLM-Cited Feature Rationales for Next Basket Repurchase Recommendation 提出基于LLM的特征理由以改善下一篮子复购推荐 large language model
20 Generating Workflow DAGs from Natural Language with Non-Reasoning LLMs 提出神经符号分解方法以生成企业工作流DAG large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
21 CoJEPA: Combining Contrastive Learning and JEPA for Global-Local Music Representations 提出CoJEPA以解决音乐表示学习中的全局与局部信息不足问题 JEPA Joint-Embedding Predictive Architecture joint-embedding predictive architecture
22 Multimodal Adaptive Expert Selection with Text Routing and Ordinal Prototype Optimization for Sentiment Analysis 提出MAESTRO框架以解决多模态情感分析中的表示不足问题 contrastive learning multimodal
23 CAER: Causal Action Effect Reweighting for World Model Training 提出CAER以解决世界模型训练中的因果效应问题 world model world models
24 HiRS-Agent: A Hierarchical Multi-Agent System for Reliable Long-Horizon Remote Sensing Task Solving 提出HiRS-Agent以解决长时间遥感任务的可靠性问题 reinforcement learning large language model multimodal ✅
25 MedAgent-R1: Faithfulness-Aware Reinforcement Learning for Evidence-Grounded Medical Reasoning 提出MedAgent-R1以解决医疗推理中的信实性问题 reinforcement learning reward design
26 Reconciling Process Supervision with Outcome-Based Credit in Agentic Policy Optimization 提出TASPO以解决监督与信用不匹配问题 reinforcement learning distillation privileged information
27 Learning from What You Retrieve: Online RL Fine-Tuning for Semantic Retrieval 提出PAO方法以解决大规模电商检索中的优化问题 reinforcement learning distillation

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
28 Scaffolding Foundation Models into Physical-World Agents Pushes the Frontier of Long-Horizon Navigation 提出NavMCP框架以解决长时间导航中的决策与执行问题 Unitree foundation model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页