cs.LG（2025-04-28）

📊 共 19 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (9 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (9 🔗2) 支柱五：交互与反应 (Interaction & Reaction) (1)

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

#题目一句话要点标签🔗⭐
1 An Automated Reinforcement Learning Reward Design Framework with Large Language Model for Cooperative Platoon Coordination 提出基于大语言模型的强化学习奖励函数自动设计框架，用于解决车队协同控制问题。 reinforcement learning reward design large language model
2 Modular Machine Learning: An Indispensable Path towards New-Generation Large Language Models 提出模块化机器学习框架，提升大语言模型的可解释性与适应性。 representation learning large language model
3 Contextures: The Mechanism of Representation Learning 提出Contexture理论，统一表征学习框架，揭示预训练机制。 representation learning foundation model
4 Interactive Double Deep Q-network: Integrating Human Interventions and Evaluative Predictions in Reinforcement Learning of Autonomous Driving 提出交互式双深度Q网络(iDDQN)，融合人类干预提升自动驾驶强化学习性能。 reinforcement learning DRL
5 Representation Learning on a Random Lattice 提出基于随机格子的表征学习模型，提升深度神经网络的可解释性。 representation learning
6 Accurate and Diverse LLM Mathematical Reasoning via Automated PRM-Guided GFlowNets 提出基于自动PRM引导的GFlowNets，提升LLM数学推理的准确性和多样性 reinforcement learning large language model
7 Rulebook: bringing co-routines to reinforcement learning environments 提出Rulebook，一种基于协程的领域特定语言，简化强化学习环境构建。 reinforcement learning
8 Soft-Label Caching and Sharpening for Communication-Efficient Federated Distillation SCARLET：面向通信高效联邦蒸馏的软标签缓存与锐化框架 distillation ✅
9 Quantifying Memory Utilization with Effective State-Size 提出有效状态大小(ESS)以量化序列模型内存利用率，并用于模型优化。 distillation large language model

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#题目一句话要点标签🔗⭐
10 Towards Robust Multimodal Physiological Foundation Models: Handling Arbitrary Missing Modalities 提出PhysioOmni，解决多模态生理信号分析中模态缺失及泛化性问题。 foundation model multimodal
11 Can Large Language Models Learn Formal Logic? A Data-Driven Training and Evaluation Framework 提出数据驱动框架，评估大语言模型在布尔逻辑证明中的推理能力 large language model
12 If Concept Bottlenecks are the Question, are Foundation Models the Answer? 研究VLM监督下的概念瓶颈模型，揭示其概念质量与专家标注的差异 foundation model ✅
13 Intelligent4DSE: Optimizing High-Level Synthesis Design Space Exploration with Graph Neural Networks and Large Language Models Intelligent4DSE：利用图神经网络和大型语言模型优化高层次综合设计空间探索 large language model
14 Towards Faster and More Compact Foundation Models for Molecular Property Prediction 通过剪枝JMP模型，实现分子性质预测中更快速紧凑的Foundation模型 foundation model ✅
15 Improving Reasoning Performance in Large Language Models via Representation Engineering 通过表征工程提升大语言模型推理能力 large language model
16 FineQ: Software-Hardware Co-Design for Low-Bit Fine-Grained Mixed-Precision Quantization of LLMs FineQ：面向LLM低比特细粒度混合精度量化的软硬件协同设计 large language model
17 Graph-Based Spectral Decomposition for Parameter Coordination in Language Model Fine-Tuning 提出基于图谱分解的参数协同优化算法，提升大语言模型微调效率与结构感知能力。 large language model
18 R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference R-Sparse：一种免训练的激活稀疏化方法，用于高效LLM推理 large language model

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
19 A Cryptographic Perspective on Mitigation vs. Detection in Machine Learning 从密码学视角研究机器学习中对抗样本的检测与缓解 OMOMO

⬅️ 返回 cs.LG 首页 · 🏠 返回主页