cs.LG（2026-08-07）

📊 共 20 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (11 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (9)

🔬 支柱二：RL算法与架构 (RL & Architecture) (11 篇)

#题目一句话要点标签🔗⭐
1 Beyond Foundation Models: Dimension-Aware Neural Architecture Search with Small-Data Representation Models for Cryocooler Lifetime Prediction 提出小数据表示模型以解决冷却器寿命预测问题 representation learning foundation model
2 Dueling World Models: Advantage-Style Action Channels for Common-Mode Distractor Rejection 提出对抗式世界模型以解决干扰因素拒绝问题 world model world models latent dynamics
3 Beyond Myopic World Models: Long-Horizon End-to-End Training for Direct Future Prediction 提出直接预测世界模型以解决长时间预测问题 world model world models
4 Trajectory-Relative Hindsight Distillation for Agentic Reinforcement Learning 提出TRIAL框架以解决稀疏奖励分配问题 reinforcement learning distillation
5 From Optimal Actions to World Models: Identifiability of Transition Kernels in Discounted MDPs 通过最优动作识别MDP转移核的可识别性问题 world model world models
6 Momba: Network Modernization Improves Multi-Objective Reinforcement Learning 通过网络现代化提升多目标强化学习的性能 reinforcement learning deep reinforcement learning
7 Aftab: A Comprehensive Benchmark of CNN Encoders and Advanced Value Functions in Parallelized Q-Networks 提出Aftab框架以优化并行化Q网络中的CNN编码器 reinforcement learning deep reinforcement learning policy learning ✅
8 FUSE: Feature-Wise Unified Specialization with Cross-Column Exchange for Mixed-Type Tabular Flow Matching 提出FUSE以解决混合类型表格数据生成问题 flow matching
9 Interpretable reinforcement learning with decision-tree pruning 提出决策树修剪方法以提高强化学习的可解释性 reinforcement learning
10 Beyond Isolation: Unlocking Reinforcement Learning Component Synergy for Sample-Efficient Continuous Control 提出ROSER框架以提升强化学习的样本效率 reinforcement learning
11 Learning Suffers More Than the Policy Class Under Partial Observability: A Closed-Form Analysis 提出闭式分析以解决部分可观测性下的学习问题 reinforcement learning deep reinforcement learning

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

#题目一句话要点标签🔗⭐
12 Walkable to Whom? Capturing Subjective Variability in Walkability Perception Using Multimodal Deep Learning 提出多模态深度学习框架以解决步行可达性感知的主观差异问题 multimodal
13 A foundation-model approach to pediatric headache classification from rs-fMRI 提出基于NeuroSTORM的儿童头痛分类方法 foundation model
14 Multi-Level Modeling of Large Language Model Inference Latency and Energy via Hybrid Analytical--Machine-Learning Predictors 提出HYMELL框架以解决LLM推理延迟与能耗问题 large language model
15 An AI4AI Framework for Visual Token Pruning 提出AI4AI框架以实现视觉标记剪枝 large language model multimodal
16 Stochastic Autoregressive Learning 提出随机自回归学习模型以改进LLM输出生成 chain-of-thought
17 Conformal Fusion Under Missing Modalities 提出模态条件的保形融合以解决缺失模态问题 multimodal
18 Every Cache Entry Earns Its Place: Global Allocation of Resolution and Coverage for KV Cache Compression 提出GraceKV以解决KV缓存压缩中的资源分配问题 large language model
19 CubicQuant: Parametric Non-Uniform Codebooks for High-Throughput LLM Inference with 1-8-Bit Weights 提出CubicQuant以解决大语言模型推理中的权重量化问题 large language model
20 Solver-Guided Reasoning for Mixed-Equilibrium Strategies 提出混合策略决策树以优化复杂游戏中的均衡推理 large language model

⬅️ 返回 cs.LG 首页 · 🏠 返回主页