cs.LG（2025-09-06）
📊 共 11 篇论文
🎯 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) (3)
支柱一：机器人控制 (Robot Control) (2)
🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Fisher Random Walk: Automatic Debiasing Contextual Preference Inference for Large Language Model Evaluation | 提出Fisher随机游走方法，自动去偏上下文偏好推断，用于大规模语言模型评估。 | large language model | ||
| 2 | time2time: Causal Intervention in Hidden States to Simulate Rare Events in Time Series Foundation Models | 提出时间序列Transformer模型的因果干预方法，模拟罕见事件并进行压力测试。 | foundation model | ||
| 3 | Learning to Route: Per-Sample Adaptive Routing for Multimodal Multitask Prediction | 提出一种基于样本自适应路由的多模态多任务预测框架，解决数据异构和任务交互问题。 | multimodal | ||
| 4 | GraMFedDHAR: Graph Based Multimodal Differentially Private Federated HAR | GraMFedDHAR：基于图的多模态差分隐私联邦HAR框架，提升隐私保护下的活动识别精度。 | multimodal | ||
| 5 | ProfilingAgent: Profiling-Guided Agentic Reasoning for Adaptive Model Optimization | ProfilingAgent：提出Profiling引导的Agentic推理，自适应优化模型压缩。 | large language model foundation model | ||
| 6 | Finetuning LLMs for Human Behavior Prediction in Social Science Experiments | 通过微调LLM，Socrates在社会科学实验中实现更精准的人类行为预测 | large language model |
🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 7 | Causal Debiasing Medical Multimodal Representation Learning with Missing Modalities | 提出因果去偏的多模态表示学习框架，解决医学数据缺失模态下的偏差问题 | predictive model representation learning multimodal | ||
| 8 | Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies | 模型强化学习中离线与在线学习对比研究，揭示数据收集策略对性能的影响 | reinforcement learning world model model-based RL | ||
| 9 | Reinforcement Learning with Anticipation: A Hierarchical Approach for Long-Horizon Tasks | 提出基于预期学习的强化学习框架，解决长时程任务中的层级策略学习问题 | reinforcement learning geometric consistency |
🔬 支柱一：机器人控制 (Robot Control) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 10 | A Physics-Informed Neural Networks-Based Model Predictive Control Framework for $SIR$ Epidemics | 提出基于物理信息神经网络的模型预测控制框架以解决SIR流行病问题 | MPC model predictive control | ||
| 11 | Simulation Priors for Data-Efficient Deep Learning | SimPEL：利用仿真先验提升深度学习在数据稀缺场景下的效率 | sim-to-real reinforcement learning |