cs.LG（2026-07-28）

📊 共 16 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (8) 支柱二：RL算法与架构 (RL & Architecture) (6) 支柱一：机器人控制 (Robot Control) (1) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (8 篇)

#题目一句话要点标签🔗⭐
1 Empirical Evaluation of Out-Of-Distribution Performance of Tabular Foundation Models 评估表格基础模型在分布外性能的表现 foundation model
2 Minimizing Targeted Activations: Input-Only Suppression of Evaluation-Awareness Latents in Large Language Models 提出输入侧抑制方法以解决大型语言模型的评估意识问题 large language model
3 DynaBridge: Dynamic Summary-Guided Cross-Task Multimodal Fusion for DASS-Structured Mental Health Assessment 提出DynaBridge以解决DASS结构心理健康评估中的多模态融合问题 multimodal
4 Neurai-VN Benchmark: Standardized Machine Learning Models for Multimodal Digital Phenotyping in Mental Health Classification 提出Neurai-VN基准以解决心理健康分类中的数据异质性问题 multimodal
5 Rethinking CD: A Reproducibility Study and Extension on the Ineffectiveness of Contrastive Decoding at Mitigating Object Hallucinations in MLLMs 重新审视对比解码以解决多模态大语言模型中的物体幻觉问题 large language model multimodal visual grounding
6 Tools Are Not Islands: Set-Level Tool Retrieval for LLM Agents via Query-Conditioned Hyperedge Prediction 提出HYSET以解决LLM代理工具检索问题 large language model
7 Guiding Posterior Exploration with Optimizer-Derived Geometry 提出基于优化器几何的后验探索指导方法以提高采样效率 multimodal
8 Retraction-Free Optimization over the Stiefel Manifold for the LoRA Fine-Tuning 提出无回撤优化算法以解决LoRA微调问题 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🔗⭐
9 Reinformed Dreamer: An Asymmetric World Model Efficiently Trained through Latent Guidance 提出Reinformed Dreamer以解决特权信息表示不足问题 reinforcement learning world model world models
10 WALoMA: A Multitask Wireless Foundation Model via Adaptive Low-Rank Masked Autoencoders 提出WALoMA以解决无线数据标注稀缺问题 masked autoencoder MAE foundation model
11 Learning from the Unseen: Offline Reinforcement Learning with Hidden Actions 提出LURE以解决离线强化学习中的隐藏动作问题 reinforcement learning offline RL offline reinforcement learning
12 Contrastive Representation Learning of Longitudinal Disease Trajectories on Temporal Graphs 提出对比表示学习框架以解析纵向疾病轨迹 representation learning contrastive learning
13 Reinforcement Learning for Code Optimization 提出基于强化学习的代码优化方法以解决执行时间问题 reinforcement learning
14 A Unified Algorithmic Framework for Hybrid Reinforcement Learning in Tabular MDPs with Shifted Transition Dynamics 提出统一算法框架以解决带有转移动态偏移的混合强化学习问题 reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
15 Decision-Level Hijacking: Injecting Cognitive Bias into Large Language Models via Bit-Flip Attacks 提出CogBias框架以解决大语言模型的决策级劫持问题 manipulation large language model

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
16 A Physics-Informed Neural Operator for Thermal Ranking of Low-Cost Wall Materials in Hot-Dry Climates 提出物理信息神经算子以优化热干气候低成本墙体材料的热性能 penetration

⬅️ 返回 cs.LG 首页 · 🏠 返回主页