cs.LG（2026-09-01）

📊 共 23 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (16 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗2) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (16 篇)

#题目一句话要点标签🔗⭐
1 Contribution-Aware Bandwidth Allocation for Multimodal Split Learning 提出ModalShare以解决多模态分裂学习中的带宽分配问题 multimodal
2 EEG-AS: Instance-Level Foundation Model Selection for EEG Foundation Models via Behavior Reconstruction 提出EEG-AS以解决EEG基础模型选择问题 foundation model
3 Text Capability Loss in Vision-Language Adaptation: An Attention-Sink Diagnosis 提出Sink Strength以诊断视觉语言适应中的文本能力损失问题 instruction following chain-of-thought
4 Confess What You Know: Forget-Set Misalignment with Model Knowledge in LLM Unlearning 提出CONFS框架以解决大语言模型的遗忘集不匹配问题 large language model multimodal
5 The Structure of Quantization Damage in LLMs: Why the Next Bit Should Be Spent Globally 提出全球量化策略以优化大语言模型的精度损失 large language model
6 Efficiently Estimating Optimal Hyperparameter Scaling Laws through Power-Law Entropy Search 提出PLES以高效估计超参数缩放规律 large language model
7 TRIAGE: Three-level Routing and Intelligent Agent Guidance for Efficient Execution 提出TRIAGE框架以解决ReAct模型效率问题 large language model
8 mzCache: On-Device LLM Memory Management under Multitasking 提出mzCache以解决移动设备多任务环境下的LLM内存管理问题 large language model
9 Bandits in Prod: Hyperparameter Optimization at Inference Time 提出IMABO框架以解决在线超参数优化问题 foundation model
10 Post-Training Science for Supervised Fine-Tuning 提出后训练科学以优化监督微调过程 instruction following
11 Pre-carved Niches: The Formation Dynamics of Modular Task Partitions in Early LLM Training 提出模块化任务划分动态形成机制以优化大语言模型训练 large language model
12 Modelpedia: A Catalog of Model Findings for the Meta-Science of AI 提出Modelpedia以解决AI模型知识组织问题 foundation model
13 Web Price Extraction: State of the Art and an Adaptive Browserless Implementation 提出自适应无浏览器价格提取系统以解决电商数据提取问题 large language model
14 Are You Thinking What I am Thinking? : Examining Conceptual Separation in Neural Architectures 提出概念分离分析以提升神经网络的内部表示理解 large language model ✅
15 Breaking the Structural Identity: Personalized Federated LoRA Fine-tuning under Rank Heterogeneity 提出FedRoRA以解决联邦学习中的个性化适应问题 large language model
16 Topological Steering 提出拓扑引导以增强大语言模型行为控制 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
17 REFACTOR-VLA: Unsupervised Library Learning of Typed Motor Programs 提出REFACTOR-VLA以解决长时间任务中的行为抽象问题 world model world models vision-language-action
18 NashDreamer: Model-Based Reinforcement Learning for Zero-Sum Imperfect-Information Games 提出NashDreamer以解决零和不完全信息博弈中的模型学习问题 reinforcement learning dreamer
19 CopyShield: A Cross-Level Benchmark of Copyright Defenses in LLMs 提出CopyShield以解决大语言模型版权防御评估不一致问题 DPO direct preference optimization large language model ✅
20 Explore More, Drift Less: Outcome-Only Reinforcement Learning Can Suffice for Long-Horizon Interactive Agents 提出CANOPY以解决长时间交互任务中的信号稀缺与策略漂移问题 reinforcement learning ✅
21 Subliminal Learning as Trait-Direction Drift: A Mechanism and Targeted Control under SFT Distillation 提出特征方向漂移机制以控制隐性学习问题 distillation
22 Conditional Flow Matching for ML-Based Inverse Design Problems 提出条件流匹配以解决基于机器学习的逆向设计问题 flow matching

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
23 Provably Safe Sim-to-Real Transfer 提出安全的模拟到现实转移方法以解决数据收集中的安全问题 sim-to-real reinforcement learning

⬅️ 返回 cs.LG 首页 · 🏠 返回主页