cs.AI（2026-09-04）

📊 共 34 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (19 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (12 🔗1) 支柱一：机器人控制 (Robot Control) (3)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (19 篇)

#题目一句话要点标签🔗⭐
1 Whose record is this? Diagnosing and authorizing record use in personalized multimodal models 提出记录授权机制以解决视觉个性化中的错误记录问题 multimodal
2 PLUME: Parameter-Efficient Personalization of Large Language Models via Low-Rank User Modulation in Shared Subspaces 提出PLUME以高效个性化大型语言模型 large language model
3 Diffusion Language Models for Mobile Edge Agentic AI: Foundations, Applications, and Challenges 提出扩散语言模型以提升移动边缘智能AI的响应能力 large language model multimodal
4 Don't Drop Dropout: Optimizing Layer Sparsity for Efficient LLM Training and Inference 优化层稀疏性以提高大型语言模型的训练与推理效率 large language model
5 Trace2Tower: Transition-Aware EigenTrace Induction of Multi-Level Skills for LLM Agents 提出Trace2Tower以解决LLM代理技能层次化问题 large language model
6 Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization 提出OR-Clarify与InterOPT以解决优化模型中的不完整性问题 large language model
7 Uncensored Open-weight Models: Redistribution as the Persistence Layer 分析开放权重AI模型去中心化的安全隐患与应用 large language model
8 ACE: Adaptive Calibration-Free Expert Skipping for MoE-based LLMs 提出ACE框架以解决MoE模型中的冗余计算问题 large language model
9 AxQM: A Textbook-Scale Benchmark for Formal Proof Synthesis in a Library of Finite-Dimensional Quantum Mechanics 提出AxQM基准以评估物理领域的形式证明合成 large language model
10 LLM-Guided Program Evolution for Circle Packing: Breaking 10 Packomania Records for $28 提出Discovery Loop以优化圆形打包算法 large language model
11 Language models judge war differently when tested for alignment 研究语言模型在战争决策中的对齐评估影响 large language model
12 Better Understanding, Better Fixes? A Study of Hallucination in LLM-based Automated Program Repair 深入分析LLM在自动程序修复中的幻觉现象 large language model
13 PRISM-Bench: An Audio-Centric Diagnostic Benchmark for Text-to-Audio-Video Generation 提出PRISM-Bench以解决T2AV生成中音频评估不足的问题 visual grounding
14 LLM-Assisted Behavioural and Scenario Augmentation for Agent-Based Energy Adoption Models 提出LLM辅助的行为与场景增强框架以优化能源采纳模型 large language model
15 DODR: Deterministic Operator-Driven Reasoning in Latent Space 提出DODR架构以解决复杂逻辑推理中的三大缺陷 large language model
16 Shadow Queries for Private Retrieval in Vector Databases 提出SHAQ以解决向量数据库中的隐私检索问题 large language model
17 DCFA: Dual-view Causal-inspired Attribution for Failure Reasoning in LLM-based Multi-agent Systems 提出DCFA以解决LLM多智能体系统中的故障归因问题 large language model
18 Aplaud: Adaptive Personalized Low-Rank Decomposition for User-Specific LLM 提出Aplaud以解决个性化大语言模型的低秩分解问题 large language model
19 ERPBench: Evaluating LLM Agents for Enterprise Decision-Making Across Competitive Market Ecologies 提出ERPBench以评估企业决策中的LLM代理在竞争市场中的表现 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (12 篇)

#题目一句话要点标签🔗⭐
20 MM-IFEval-Pro: A Multilingual and Attack-Resistant Benchmark for Instruction-Following in Vision-Language Models 提出MM-IFEval-Pro以解决多模态指令跟随评估不足问题 reinforcement learning multimodal instruction following
21 Wireless Foundation Models: State-of-the-Art and Open Challenges 系统分析无线基础模型以解决无线数据表示学习问题 representation learning foundation model
22 Unifying ICL, SFT, KL-Regularized RL Through a Bayesian Lens 通过贝叶斯视角统一ICL、SFT与KL正则化RL RLHF distillation large language model
23 Reinforcement Learning for Sequential Solar PV Policy Design under Uncertainty: An Agent-Based Approach 提出基于强化学习的太阳能光伏政策设计方法以应对不确定性 reinforcement learning PPO SAC
24 What Matters in On-Policy Distillation? A Perspective on Data Efficiency and Data Selection 提出基于困难样本选择的蒸馏训练方法以提升数据效率 distillation large language model
25 CoSkill: Joint Reinforcement Learning of Reasoning and Meta-Skill Agents for Hierarchical Skill Evolution 提出CoSkill框架以解决技能演化与策略优化的耦合问题 reinforcement learning large language model ✅
26 Predicting Spatiotemporal Mobile Sensing-Based PM2.5 Concentrations Using Low-Rank Adapted Spatially Attentive Graph Neural Network 提出SA-GNN以解决城市PM2.5浓度预测问题 MAE spatiotemporal
27 From Language Models to World-Acting Systems: Progress and Limits of Agentic AI across Digital, Social, Virtual, and Physical Environments 提出合理授权框架以解决代理人工智能的局限性 world model world models large language model
28 RISE: Recursive Improvement via Self-Extrapolating Policy Distillation 提出RISE以解决语言模型蒸馏中的教师质量瓶颈问题 distillation
29 GUT: Quantifying and Optimizing the Reasoning Uncertainty of LLMs via Graph Complexity 提出GUT方法以量化和优化大型语言模型的推理不确定性 reinforcement learning large language model
30 A Unified Physics-Aware Quantum Machine Learning Framework across Power GaN HEMTs and Logic Nanowire FETs: Predicting Unseen Process Splits and Held-Out Geometry Combinations with Lower Error and Tighter Split-to-Split Variability 提出统一的物理感知量子机器学习框架以提高器件建模精度 reinforcement learning PPO MAE
31 MZ-Rain: Moisture-Budget-Guided Zero-Inflated Model for Station-Level Precipitation Nowcasting 提出MZ-Rain以解决站级降水短期预报中的物理建模与零膨胀问题 predictive model MAE

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#题目一句话要点标签🔗⭐
32 Large Language Models for HVAC Operations in Building Energy Systems: A Critical Review of Methods, Applications, and Deployment Readiness 系统评估大型语言模型在HVAC操作中的应用与部署准备 MPC model predictive control reinforcement learning
33 Cost-Aware Hierarchical Multi-Agent Ransomware Detection and Family Attribution 提出成本感知的层次化多智能体勒索软件检测方法 manipulation large language model multimodal
34 CABAL: Multi-Agent Simulacra for Tracing the Effects of Collusive Bidding in Peer Review 提出CABAL框架以研究同行评审中的串通竞标问题 manipulation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页