cs.LG（2026-02-14）

📊 共 10 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (6 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱一：机器人控制 (Robot Control) (1)

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

#	题目	一句话要点	标签	🔗	⭐
1	HBVLA: Pushing 1-Bit Post-Training Quantization for Vision-Language-Action Models	提出HBVLA以解决视觉-语言-动作模型的量化问题	vision-language-action VLA instruction following
2	MEMTS: Internalizing Domain Knowledge via Parameterized Memory for Retrieval-Free Domain Adaptation of Time Series Foundation Models	提出MEMTS，通过参数化记忆内化领域知识，实现时间序列基础模型的免检索领域自适应。	foundation model
3	sleep2vec: Unified Cross-Modal Alignment for Heterogeneous Nocturnal Biosignals	提出sleep2vec，通过跨模态对齐统一建模异构夜间生理信号，提升睡眠分析任务性能。	foundation model multimodal
4	Benchmark Leakage Trap: Can We Trust LLM-based Recommendation?	揭示LLM推荐系统中的基准泄漏陷阱，评估可靠性面临挑战	large language model foundation model	✅
5	On Representation Redundancy in Large-Scale Instruction Tuning Data Selection	提出压缩表征数据选择(CRDS)框架，解决指令微调数据选择中的表征冗余问题。	large language model	✅
6	Attention Head Entropy of LLMs Predicts Answer Correctness	提出Head Entropy方法，利用LLM注意力头熵预测答案正确性，提升领域外泛化能力。	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	NeuroMambaLLM: Dynamic Graph Learning of fMRI Functional Connectivity in Autistic Brains Using Mamba and Language Model Reasoning	NeuroMambaLLM：利用Mamba和语言模型推理动态学习自闭症大脑的fMRI功能连接	Mamba large language model multimodal
8	Pawsterior: Variational Flow Matching for Structured Simulation-Based Inference	Pawsterior：变分流匹配框架，用于结构化领域的模拟推断	flow matching
9	Cast-R1: Learning Tool-Augmented Sequential Decision Policies for Time Series Forecasting	Cast-R1：提出工具增强的序列决策策略，用于时序预测。	reinforcement learning policy learning curriculum learning	✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
10	Mean Flow Policy with Instantaneous Velocity Constraint for One-step Action Generation	提出基于瞬时速度约束的平均流策略，用于机器人操作任务中的单步动作生成。	manipulation reinforcement learning

⬅️ 返回 cs.LG 首页 · 🏠 返回主页