cs.LG(2026-06-23)
📊 共 12 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) (6)
支柱二:RL算法与架构 (RL & Architecture) (4 🔗1)
支柱四:生成式动作 (Generative Motion) (1)
支柱一:机器人控制 (Robot Control) (1)
🔬 支柱九:具身大模型 (Embodied Foundation Models) (6 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | A Fair Evaluation of Graph Foundation Models for Node Property Prediction | 提出公平评估图基础模型以解决节点属性预测问题 | foundation model | ||
| 2 | Natural Identifiers for Privacy and Data Audits in Large Language Models | 提出自然标识符以解决大语言模型隐私审计问题 | large language model | ||
| 3 | Grad Detect: Gradient-Based Hallucination Detection in LLMs | 提出Grad Detect以解决LLMs的幻觉检测问题 | large language model | ||
| 4 | Reasoning as Attractor Dynamics: Latent Memory Retrieval via Gibbs-Weighted Energy Minimization | 提出基于吉布斯加权能量最小化的推理吸引子动态机制 | large language model | ||
| 5 | Parallel Manifold Steering: Efficient Adaptation of Large Associative Memories via Residual Energy Shaping | 提出H-Res以解决大规模变换器模型适应性问题 | foundation model | ||
| 6 | Uniform Sampling from High-dimensional Spectral Norm Balls | 提出统一采样方法以解决高维谱范数球体采样问题 | large language model |
🔬 支柱二:RL算法与架构 (RL & Architecture) (4 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 7 | AsyncOPD: How Stale Can On-Policy Distillation Be? | 提出AsyncOPD以解决异步策略蒸馏中的数据陈旧问题 | reinforcement learning distillation large language model | ||
| 8 | Holistic Data Scheduler for LLM Pre-training via Multi-Objective Reinforcement Learning | 提出整体数据调度器以解决LLM预训练中的数据混合问题 | reinforcement learning SAC large language model | ||
| 9 | NeuroSonic: Conditional Flow Matching for EEG-to-Speech Reconstruction | 提出NeuroSonic以解决EEG到语音重建的挑战 | flow matching | ✅ | |
| 10 | Blockwise Policy-Drift Gating for On-Policy Distillation | 提出块状策略漂移门控以解决长时间推理任务中的脆弱性问题 | distillation |
🔬 支柱四:生成式动作 (Generative Motion) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 11 | Information-Theoretic Classifier-Free Guidance with Adaptive Schedule Optimization | 提出信息论框架优化无分类器引导以解决一致性与覆盖性权衡问题 | classifier-free guidance |
🔬 支柱一:机器人控制 (Robot Control) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 12 | PROTECT-90: A Fault Dataset for Power System Protection | 提出PROTECT-90数据集以解决高压电力系统保护研究缺乏标准数据的问题 | domain randomization |