cs.LG（2025-05-27）

📊 共 42 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (23 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (16 🔗2) 支柱一：机器人控制 (Robot Control) (1) 支柱四：生成式动作 (Generative Motion) (1 🔗1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (23 篇)

#题目一句话要点标签🔗⭐
1 Let Me Think! A Long Chain-of-Thought Can Be Worth Exponentially Many Short Ones 提出长链思维以解决推理效率问题 large language model chain-of-thought
2 DeCAF: Decentralized Consensus-And-Factorization for Low-Rank Adaptation of Foundation Models 提出DeCAF以解决去中心化LoRA的共识干扰问题 large language model foundation model
3 Multimodal Federated Learning: A Survey through the Lens of Different FL Paradigms 提出多模态联邦学习的分类框架以应对不同FL范式的挑战 multimodal
4 LaX: Boosting Low-Rank Training of Foundation Models via Latent Crossing 提出LaX以提升基础模型低秩训练性能 foundation model
5 Towards Robust Assessment of Pathological Voices via Combined Low-Level Descriptors and Foundation Model Representations 提出VOQANet及其增强版以解决病理声音评估问题 foundation model
6 Efficient Large Language Model Inference with Neural Block Linearization 提出神经块线性化以加速大语言模型推理 large language model ✅
7 LLaMEA-BO: A Large Language Model Evolutionary Algorithm for Automatically Generating Bayesian Optimization Algorithms 提出LLaMEA-BO以自动生成贝叶斯优化算法 large language model ✅
8 Generalizable Heuristic Generation Through Large Language Models with Meta-Optimization 提出Meta-Optimization框架以解决组合优化问题 large language model
9 PreGenie: An Agentic Framework for High-quality Visual Presentation Generation 提出PreGenie框架以解决视觉演示生成中的多模态理解问题 large language model multimodal
10 From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs 提出多维锥体框架以探讨LLMs中的真理表示问题 large language model
11 PolarGrad: A Class of Matrix-Gradient Optimizers from a Unifying Preconditioning Perspective 提出PolarGrad以提升深度学习优化效率 large language model
12 MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement 提出MLE-STAR以解决机器学习工程中的模型选择与深度探索问题 large language model
13 A Convergence Theory for Diffusion Language Models: An Information-Theoretic Perspective 提出扩散语言模型收敛理论以解决理论理解不足问题 large language model
14 Improving LLM-based Global Optimization with Search Space Partitioning 提出HOLLM算法以解决高维搜索空间优化问题 large language model
15 Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders 提出混合解码器以解决多层感知机可解释性问题 large language model ✅
16 Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning 提出4位浮点量化框架以解决扩散模型的量化挑战 large language model
17 PoisonSwarm: Universal Harmful Information Synthesis via Model Crowdsourcing 提出PoisonSwarm以解决有害信息合成的多样性与可靠性问题 large language model
18 Pause Tokens Strictly Increase the Expressivity of Constant-Depth Transformers 引入暂停符号以提升常深度变换器的表达能力 chain-of-thought
19 FireQ: Fast INT4-FP8 Kernel and RoPE-aware Quantization for LLM Inference Acceleration 提出FireQ以解决大语言模型推理加速问题 large language model
20 Convergence of Clipped-SGD for Convex $(L_0,L_1)$-Smooth Optimization with Heavy-Tailed Noise 提出高概率收敛界限以解决重尾噪声下的优化问题 large language model
21 ChemHAS: Hierarchical Agent Stacking for Enhancing Chemistry Tools 提出ChemHAS以减少化学工具的预测误差 large language model
22 'Hello, World!': Making GNNs Talk with LLMs 提出图语言网络以提升图神经网络的可解释性与性能 large language model
23 Can Past Experience Accelerate LLM Reasoning? 提出SpeedupLLM框架以加速大语言模型推理 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (16 篇)

#题目一句话要点标签🔗⭐
24 TuneComp: Joint Fine-tuning and Compression for Large Foundation Models 提出TuneComp以解决大规模基础模型的联合微调与压缩问题 distillation foundation model
25 A Cross Modal Knowledge Distillation & Data Augmentation Recipe for Improving Transcriptomics Representations through Morphological Features 提出跨模态知识蒸馏与数据增强方法以提升转录组学表现 distillation foundation model multimodal
26 Foundation Model Hidden Representations for Heart Rate Estimation from Auscultation 利用基础模型隐含表示进行心率估计，提升听诊技术的准确性 MAE foundation model
27 TabReason: A Reinforcement Learning-Enhanced Reasoning LLM for Explainable Tabular Data Prediction 提出TabReason以解决表格数据预测的可解释性问题 reinforcement learning predictive model large language model
28 Deep Reinforcement Learning Agents are not even close to Human Intelligence 提出HackAtari以解决深度强化学习智能不足问题 reinforcement learning deep reinforcement learning
29 Topology-Aware and Highly Generalizable Deep Reinforcement Learning for Efficient Retrieval in Multi-Deep Storage Systems 提出基于深度强化学习的框架以解决多深度存储系统的检索问题 reinforcement learning deep reinforcement learning
30 Hierarchical Reinforcement Learning with Uncertainty-Guided Diffusional Subgoals 提出不确定性引导的扩散子目标以解决层次强化学习问题 reinforcement learning diffusion policy
31 Simple yet Effective Graph Distillation via Clustering 提出ClustGDD以解决图神经网络训练中的计算开销问题 representation learning distillation
32 Semi-supervised Clustering Through Representation Learning of Large-scale EHR Data 提出SCORE框架以解决电子健康记录数据建模挑战 predictive model representation learning
33 Accelerating RL for LLM Reasoning with Optimal Advantage Regression 提出A*-PO以解决RL在LLM推理中的高计算开销问题 reinforcement learning PPO large language model ✅
34 A Framework for Adversarial Analysis of Decision Support Systems Prior to Deployment 提出对决策支持系统的对抗性分析框架以增强安全性 reinforcement learning deep reinforcement learning DRL
35 Universal Value-Function Uncertainties 提出通用价值函数不确定性以解决强化学习中的不确定性问题 reinforcement learning offline RL distillation
36 HAD: Hybrid Architecture Distillation Outperforms Teacher in Genomic Sequence Modeling 提出混合架构蒸馏方法以提升基因序列建模性能 distillation
37 A reinforcement learning agent for maintenance of deteriorating systems with increasingly imperfect repairs 提出强化学习代理以优化逐渐恶化系统的维护策略 reinforcement learning
38 Apprenticeship learning with prior beliefs using inverse optimization 提出逆优化框架以增强逆强化学习的学习能力 reinforcement learning inverse reinforcement learning
39 Sparsified State-Space Models are Efficient Highway Networks 提出Simba方法以提高状态空间模型的效率 Mamba SSM ✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
40 Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement Learning 提出多层次认证防御以应对离线强化学习中的毒化攻击 manipulation reinforcement learning offline RL

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
41 Conditional Diffusion Models with Classifier-Free Gibbs-like Guidance 提出无分类器引导的吉布斯采样以解决扩散模型样本多样性问题 classifier-free guidance ✅

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

#题目一句话要点标签🔗⭐
42 Towards Operational Automated Greenhouse Gas Plume Detection 提出多任务模型以解决温室气体探测中的关键挑战 spatiotemporal

⬅️ 返回 cs.LG 首页 · 🏠 返回主页