cs.LG（2026-08-21）

📊 共 11 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (6 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Thermo-FL: Thermal-Aware Robust Federated Fine-Tuning of Large Language Models for Edge AI	提出Thermo-FL以解决边缘AI中的热管理与更新安全问题	large language model
2	COEC: Calibrated Orthogonal-Equivalence Compensation for Structured Pruning of Large Language Models	提出COEC以解决大语言模型结构化剪枝后的性能下降问题	large language model
3	Trojaning the Alignment: Stealthy Backdoor Attacks against Graph Foundation Models	提出STAG框架以解决图基础模型的隐蔽后门攻击问题	foundation model	✅
4	Jacobian-guided Noise Injection for Quantization Robustness in Large Language Models	提出雅可比引导噪声注入以增强大语言模型的量化鲁棒性	large language model
5	ConceptTS: LLM-Guided Concept Bottlenecks for Interpretable Multivariate Time-Series Forecasting	提出ConceptTS以解决多变量时间序列预测的可解释性问题	large language model
6	Fine-tuning LLMs for Tourist Trajectory Prediction using Field Experiment Data	利用大语言模型优化游客轨迹预测以应对环境变化	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	Decoupling Policy Extraction for Offline Reinforcement Learning	提出解耦策略提取以解决离线强化学习中的政策改进问题	reinforcement learning offline RL offline reinforcement learning
8	AudioWorldSim: Realistic Binaural Audio Datasets For World Models	提出AudioWorldSim以生成逼真的双耳音频数据集	world model world models	✅
9	Tydra: An Efficient Hybrid Model for Tabular Data	提出Tydra以平衡表格数据建模的效率与准确性	SSM state space model foundation model
10	Reinforcement Learning for Continuous-Time Jump Markov Decision Processes with Applications to Network Dynamic Pricing	提出强化学习方法解决连续时间跳跃马尔可夫决策过程中的动态定价问题	reinforcement learning

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
11	A Critical Audit of Spatiotemporal Forecasting Benchmark Datasets and Baselines	提出对时空预测基准数据集的批判性审计以提升模型评估可靠性	spatiotemporal

⬅️ 返回 cs.LG 首页 · 🏠 返回主页