cs.LG（2026-03-26）

📊 共 17 篇论文

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (9) 支柱九：具身大模型 (Embodied Foundation Models) (7) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (9 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale	推出首个万亿参数科学多模态基础模型Intern-S1-Pro，提升通用与科学领域能力。	reinforcement learning foundation model multimodal
2	Layer-Specific Lipschitz Modulation for Fault-Tolerant Multimodal Representation Learning	提出层特异性Lipschitz调制方法，提升多模态表征学习在故障下的鲁棒性	representation learning multimodal
3	Spatiotemporal System Forecasting with Irregular Time Steps via Masked Autoencoder	提出Physics-Spatiotemporal Masked Autoencoder，用于预测具有不规则时间步长的高维时空系统。	masked autoencoder spatiotemporal
4	Cooperative Deep Reinforcement Learning for Fair RIS Allocation	提出基于合作深度强化学习的公平RIS资源分配方案，解决多小区无线网络负载不均问题。	reinforcement learning deep reinforcement learning
5	Vision Hopfield Memory Networks	提出Vision Hopfield Memory Network，提升视觉任务的解释性和数据效率。	Mamba foundation model multimodal
6	Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes	提出Top-K局部支持匹配，解决LLM在长序列On-Policy蒸馏中的不稳定性问题	distillation large language model
7	Offline Decision Transformers for Neural Combinatorial Optimization: Surpassing Heuristics on the Traveling Salesman Problem	利用离线决策Transformer解决TSP问题，超越传统启发式算法	reinforcement learning offline RL decision transformer
8	The Symmetric Perceptron: a Teacher-Student Scenario	提出对称感知器师生框架，解决任意样本密度下的植入推断问题。	teacher-student
9	Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model	提出HIVE框架，通过在线验证提示选择，高效训练大型推理模型的强化学习。	reinforcement learning large language model

🔬 支柱九：具身大模型 (Embodied Foundation Models) (7 篇)

#	题目	一句话要点	标签	🔗	⭐
10	Missing-Aware Multimodal Fusion for Unified Microservice Incident Management	ARMOR：针对微服务事件管理的缺失感知多模态融合框架	multimodal
11	On Neural Scaling Laws for Weather Emulation through Continual Training	通过持续训练研究天气模拟的神经标度律，实现高效资源分配	foundation model
12	GlowQ: Group-Shared LOw-Rank Approximation for Quantized LLMs	GlowQ：面向量化LLM的分组共享低秩近似方法，提升效率与精度。	large language model
13	How Pruning Reshapes Features: Sparse Autoencoder Analysis of Weight-Pruned Language Models	利用稀疏自编码器分析权重剪枝对语言模型特征的影响	large language model
14	A CDF-First Framework for Free-Form Density Estimation	提出CDF优先框架以解决自由形式密度估计问题	multimodal
15	Epistemic Compression: The Case for Deliberate Ignorance in High-Stakes AI	针对高风险AI领域，提出基于数据时效性的认知压缩方法，提升模型鲁棒性。	foundation model
16	MobileDev-Bench: A Comprehensive Benchmark for Evaluating Language Models on Mobile Application Development	MobileDev-Bench：用于评估语言模型在移动应用开发中的综合基准	large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
17	Maximum Entropy Behavior Exploration for Sim2Real Zero-Shot Reinforcement Learning	提出FB-MEBE算法，用于四足机器人Sim2Real零样本强化学习中的行为探索。	quadruped sim2real reinforcement learning

⬅️ 返回 cs.LG 首页 · 🏠 返回主页