cs.LG（2025-11-21）

📊 共 18 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) (10 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (7 🔗1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗⭐
1 Adaptive Layer-Wise Transformations for Post-Training Quantization of Large Language Models 提出自适应层级变换框架，用于大语言模型后训练量化，显著提升低比特量化性能。 large language model
2 Layer-Wise High-Impact Parameter Ratio Optimization in Post-Training Quantization for Large Language Models 提出层级高影响参数比率优化以解决LLM量化问题 large language model
3 PrismSSL: One Interface, Many Modalities; A Single-Interface Library for Multimodal Self-Supervised Learning PrismSSL：用于多模态自监督学习的统一接口库 multimodal
4 Lane-Frame Quantum Multimodal Driving Forecasts for the Trajectory of Autonomous Vehicles 提出基于量子计算的车道框架多模态驾驶轨迹预测模型，提升自动驾驶安全性。 multimodal
5 FIRM: Federated In-client Regularized Multi-objective Alignment for Large Language Models 提出FIRM：一种面向大语言模型的联邦客户端正则化多目标对齐方法 large language model
6 ReBaPL: Repulsive Bayesian Prompt Learning 提出ReBaPL，通过排斥贝叶斯提示学习提升大模型在下游任务中的泛化能力。 foundation model multimodal
7 ToC: Tree-of-Claims Search with Multi-Agent Language Models 提出ToC框架，利用多智能体语言模型进行专利声明的树搜索优化。 large language model chain-of-thought ✅
8 End-to-End Transformer Acceleration Through Processing-in-Memory Architectures 提出基于存内计算架构的Transformer端到端加速方案，解决计算、访存和复杂度瓶颈。 large language model
9 Why Do Language Model Agents Whistleblow? 研究LLM智能体在不当行为场景下的“吹哨”行为，揭示道德倾向与任务复杂度的影响 large language model
10 PersonalizedRouter: Personalized LLM Routing via Graph-based User Preference Modeling 提出 PersonalizedRouter，通过图建模用户偏好实现个性化LLM路由。 large language model

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

#题目一句话要点标签🔗⭐
11 Mask the Redundancy: Evolving Masking Representation Learning for Multivariate Time-Series Clustering 提出EMTC方法，通过演进式掩码学习提升多元时间序列聚类性能。 representation learning contrastive learning TAMP
12 CroTad: A Contrastive Reinforcement Learning Framework for Online Trajectory Anomaly Detection 提出CroTad，一个用于在线轨迹异常检测的对比强化学习框架。 reinforcement learning deep reinforcement learning contrastive learning
13 Dissecting Quantum Reinforcement Learning: A Systematic Evaluation of Key Components 系统评估量子强化学习关键组件，揭示混合量子-经典架构的内在机制 reinforcement learning PPO
14 Deterministic Inference across Tensor Parallel Sizes That Eliminates Training-Inference Mismatch 提出树形结构不变核TBIK，解决大模型推理时因张量并行策略不同导致结果不一致的问题 reinforcement learning large language model ✅
15 PersonaAgent with GraphRAG: Community-Aware Knowledge Graphs for Personalized LLM 提出基于知识图谱增强检索的PersonaAgent，实现个性化LLM代理。 MAE large language model
16 Multi-Agent Pointer Transformer: Seq-to-Seq Reinforcement Learning for Multi-Vehicle Dynamic Pickup-Delivery Problems 提出MAPT框架，解决随机需求下多车辆动态取货派送问题 reinforcement learning
17 Convergence and stability of Q-learning in Hierarchical Reinforcement Learning 提出Feudal Q-learning方案，分析其在分层强化学习中的收敛性和稳定性。 reinforcement learning

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

#题目一句话要点标签🔗⭐
18 Automobile demand forecasting: Spatiotemporal and hierarchical modeling, life cycle dynamics, and user-generated online information 提出时空分层模型，融合生命周期和用户数据，提升汽车需求预测精度。 spatiotemporal

⬅️ 返回 cs.LG 首页 · 🏠 返回主页