cs.LG（2025-12-29）

📊 共 17 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) (7 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (7 🔗1) 支柱一：机器人控制 (Robot Control) (2) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
1 Splitwise: Collaborative Edge-Cloud Inference for LLMs via Lyapunov-Assisted DRL Splitwise：基于Lyapunov优化的DRL实现LLM在边缘-云协同推理的自适应切分。 reinforcement learning deep reinforcement learning DRL
2 Stochastic Siamese MAE Pretraining for Longitudinal Medical Images 提出STAMP：一种用于纵向医学图像的随机Siamese MAE预训练框架 representation learning MAE foundation model
3 Bellman Calibration for V-Learning in Offline Reinforcement Learning 提出迭代贝尔曼校准以优化离线强化学习中的价值预测 reinforcement learning offline reinforcement learning
4 Joint Link Adaptation and Device Scheduling Approach for URLLC Industrial IoT Network: A DRL-based Method with Bayesian Optimization 针对URLLC工业物联网，提出基于贝叶斯优化的DRL联合链路自适应与设备调度方法 DRL TD3
5 Eliminating Inductive Bias in Reward Models with Information-Theoretic Guidance 提出DIR方法，通过信息论优化消除奖励模型中的归纳偏置，提升RLHF性能。 reinforcement learning RLHF large language model ✅
6 On the Inverse Flow Matching Problem in the One-Dimensional and Gaussian Cases 研究一维和高斯分布下的逆流匹配问题，为流匹配模型蒸馏提供理论基础 flow matching distillation
7 Diffusion-based Decentralized Federated Multi-Task Representation Learning 提出基于扩散的去中心化联邦多任务表征学习算法，解决数据稀缺环境下的特征提取问题。 representation learning

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

#题目一句话要点标签🔗⭐
8 The Law of Multi-Model Collaboration: Scaling Limits of Model Ensembling for Large Language Models 提出多模型协作定律，揭示大语言模型集成性能的缩放规律与极限。 large language model
9 Post-Training Quantization of OpenPangu Models for Efficient Deployment on Atlas A2 针对昇腾A2，提出低比特量化方案，加速盘古模型推理并降低内存占用。 large language model chain-of-thought
10 BOAD: Discovering Hierarchical Software Engineering Agents via Bandit Optimization 提出BOAD以自动发现层次化软件工程代理解决复杂问题 large language model ✅
11 VL-RouterBench: A Benchmark for Vision-Language Model Routing 提出VL-RouterBench，用于系统评估视觉-语言模型路由系统的性能。 multimodal
12 Trustworthy Machine Learning under Distribution Shifts 针对分布偏移下的可信机器学习，研究鲁棒性、可解释性和适应性 large language model
13 FRoD: Full-Rank Efficient Fine-Tuning with Rotational Degrees for Fast Convergence FRoD：利用旋转自由度实现全秩高效微调，加速模型收敛 foundation model
14 Theoretical Foundations of Scaling Law in Familial Models 针对Familial模型，提出包含模型粒度的新型Scaling Law理论框架。 large language model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
15 Multi-Agent Framework for Threat Mitigation and Resilience in AI-Based Systems 提出多智能体框架，用于缓解和增强人工智能系统的威胁抵御能力 manipulation foundation model multimodal
16 Beyond-Diagonal Reconfigurable Intelligent Surfaces for 6G Networks: Principles, Challenges, and Quantum Horizons 面向6G网络的超对角可重构智能表面：原理、挑战与量子前沿 manipulation

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
17 SE-MLP Model for Predicting Prior Acceleration Features in Penetration Signals 提出SE-MLP模型，用于快速预测侵彻信号中的先验加速度特征，解决传统方法计算耗时问题。 penetration PULSE

⬅️ 返回 cs.LG 首页 · 🏠 返回主页