cs.LG（2025-08-25）
📊 共 13 篇论文 | 🔗 2 篇有代码
🎯 兴趣领域导航
支柱二：RL算法与架构 (RL & Architecture) (6 🔗1)
支柱九：具身大模型 (Embodied Foundation Models) (6 🔗1)
支柱八：物理动画 (Physics-based Animation) (1)
🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Characterizing the Behavior of Training Mamba-based State Space Models on GPUs | 评估Mamba基础状态空间模型在GPU上的训练行为 | Mamba SSM state space model | ||
| 2 | LLM-Driven Intrinsic Motivation for Sparse Reward Reinforcement Learning | 提出结合变分状态内在奖励与大语言模型以解决稀疏奖励问题 | reinforcement learning large language model | ||
| 3 | DRTA: Dynamic Reward Scaling for Reinforcement Learning in Time Series Anomaly Detection | 提出DRTA框架以解决时间序列异常检测中的挑战 | reinforcement learning reward shaping | ||
| 4 | VERIRL: Boosting the LLM-based Verilog Code Generation via Reinforcement Learning | 提出VERIRL框架以提升Verilog代码生成的效果 | reinforcement learning distillation | ✅ | |
| 5 | Proximal Supervised Fine-Tuning | 提出近端监督微调方法以解决模型泛化能力不足问题 | reinforcement learning PPO foundation model | ||
| 6 | Breaking Through Barren Plateaus: Reinforcement Learning Initializations for Deep Variational Quantum Circuits | 提出基于强化学习的初始化策略以解决变分量子算法的荒原高原问题 | reinforcement learning |
🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 7 | BTW: A Non-Parametric Variance Stabilization Framework for Multimodal Model Integration | 提出BTW框架以解决多模态模型集成中的噪声问题 | multimodal | ||
| 8 | AdLoCo: adaptive batching significantly improves communications efficiency and convergence for Large Language Models | 提出AdLoCo以提升大语言模型的通信效率与收敛性 | large language model | ||
| 9 | Robustness Feature Adapter for Efficient Adversarial Training | 提出适应性特征适配器以提高对抗训练效率 | foundation model | ||
| 10 | DualSparse-MoE: Coordinating Tensor/Neuron-Level Sparsity with Expert Partition and Reconstruction | 提出DualSparse-MoE以解决MoE模型的计算效率与准确性问题 | large language model | ||
| 11 | Type-Compliant Adaptation Cascades: Adapting Programmatic LM Workflows to Data | 提出类型兼容适应级联以解决复杂工作流适应问题 | large language model | ||
| 12 | FSA: An Alternative Efficient Implementation of Native Sparse Attention Kernel | 提出Flash Sparse Attention以解决稀疏注意力核效率问题 | large language model | ✅ |
🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 13 | Improving Long-term Autoregressive Spatiotemporal Predictions: A Proof of Concept with Fluid Dynamics | 提出随机推前框架以改善流体动力学的长期自回归预测 | spatiotemporal |