cs.LG（2025-08-11）
📊 共 16 篇论文
🎯 兴趣领域导航
支柱九：具身大模型 (Embodied Foundation Models) (7)
支柱二：RL算法与架构 (RL & Architecture) (6)
支柱一：机器人控制 (Robot Control) (2)
支柱八：物理动画 (Physics-based Animation) (1)
🔬 支柱九：具身大模型 (Embodied Foundation Models) (7 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | MuaLLM: A Multimodal Large Language Model Agent for Circuit Design Assistance with Hybrid Contextual Retrieval-Augmented Generation | 提出MuaLLM以解决电路设计文献检索与生成问题 | large language model multimodal | ||
| 2 | C-MAG: Cascade Multimodal Attributed Graphs for Supply Chain Link Prediction | 提出C-MAG以解决供应链链接预测中的多模态数据融合问题 | multimodal | ||
| 3 | BadPromptFL: A Novel Backdoor Threat to Prompt-based Federated Learning in Multimodal Models | 提出BadPromptFL以解决多模态模型中的后门攻击问题 | multimodal | ||
| 4 | Vision-Based Localization and LLM-based Navigation for Indoor Environments | 提出基于视觉定位与大语言模型导航的室内导航解决方案 | large language model | ||
| 5 | Selective KV-Cache Sharing to Mitigate Timing Side-Channels in LLM Inference | 提出SafeKV以解决LLM推理中的时序侧信道攻击问题 | large language model | ||
| 6 | Multi-head Transformers Provably Learn Symbolic Multi-step Reasoning via Gradient Descent | 提出多头变换器以解决符号多步推理问题 | chain-of-thought | ||
| 7 | On Understanding of the Dynamics of Model Capacity in Continual Learning | 提出有效模型容量以解决持续学习中的稳定性与可塑性困境 | 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 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 8 | WeChat-YATT: A Scalable, Simple, Efficient, and Production Ready Training Library | 提出WeChat-YATT以解决多模态RLHF训练的可扩展性问题 | reinforcement learning RLHF large language model | ||
| 9 | Pareto Multi-Objective Alignment for Language Models | 提出Pareto多目标对齐以解决语言模型的多重目标优化问题 | RLHF large language model | ||
| 10 | Learning to Align, Aligning to Learn: A Unified Approach for Self-Optimized Alignment | 提出GRAO框架以解决语言模型对齐效率低下问题 | reinforcement learning PPO DPO | ||
| 11 | GLiClass: Generalist Lightweight Model for Sequence Classification Tasks | 提出GLiClass以解决序列分类任务中的效率与准确性问题 | PPO instruction following | ||
| 12 | Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization | 提出Klear-Reasoner以解决推理模型性能再现性问题 | reinforcement learning chain-of-thought | ||
| 13 | Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning | 提出系统化评估框架以优化大语言模型的强化学习应用 | reinforcement learning PPO |
🔬 支柱一：机器人控制 (Robot Control) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 14 | Robust Anomaly Detection in O-RAN: Leveraging LLMs against Data Manipulation Attacks | 利用大语言模型解决O-RAN中的数据操控攻击问题 | manipulation large language model | ||
| 15 | Learning Robust Satellite Attitude Dynamics with Physics-Informed Normalising Flow | 提出基于物理信息的神经网络以提升卫星姿态控制的鲁棒性 | MPC model predictive control |
🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 16 | Fast and Generalizable parameter-embedded Neural Operators for Lithium-Ion Battery Simulation | 提出参数嵌入的神经算子以加速锂离子电池模拟 | PULSE |