cs.LG（2026-07-01）

📊 共 23 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) (13 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (6 🔗1) 支柱一：机器人控制 (Robot Control) (4 🔗1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (13 篇)

#题目一句话要点标签🔗⭐
1 A Geometric Perspective on Composable Emotion Steering in Text-to-Speech Models 提出几何视角下的情感引导方法以改善文本到语音合成 flow matching motion synthesis motion representation
2 A Lightweight Self-Supervised Learning Framework for Multivariate Time Series using Hierarchical-JEPA on ECG Data 提出轻量级自监督学习框架ER-JEPA以解决ECG数据分析问题 JEPA Joint-Embedding Predictive Architecture joint-embedding predictive architecture
3 Seahorse: A Unified Benchmarking Framework for Spatiotemporal Event Modeling 提出SEAHORSE框架以解决时空事件建模的比较难题 latent dynamics spatiotemporal ✅
4 From Pixels to Temporal Correlations: Learning Informative Representations for Reinforcement Learning Pre-training 提出多尺度时间对比学习以提升强化学习的样本效率 reinforcement learning policy learning contrastive learning
5 Gauging, Measuring, and Controlling Critic Complexity in Actor-Critic Reinforcement Learning 引入评论者复杂度以优化Actor-Critic强化学习方法 reinforcement learning PPO TD3
6 LeNEPA: No-Augmentation Next-Latent Prediction for Time-Series Representation Learning 提出LeNEPA以解决时间序列自监督学习中的增强依赖问题 JEPA representation learning
7 Active-GRPO: Adaptive Imitation and Self-Improving Reasoning for Molecular Optimization 提出Active-GRPO以解决分子优化中的推理效率问题 reinforcement learning imitation learning large language model
8 Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training 提出单层Transformer训练方法以优化强化学习效果 reinforcement learning large language model
9 Staleness-Learning Rate Scaling Laws for Asynchronous RLHF 提出时效性学习率缩放法则以解决异步RLHF中的过时问题 RLHF
10 Ghost in the Kernel: In-Context Learning with Efficient Transformers via Domain Generalization 提出线性变换器以解决上下文学习中的计算复杂性问题 linear attention large language model
11 Generative Modeling of Quantum Distribution with Functional Flow Matching 提出量子流匹配模型以解决量子分布学习难题 flow matching
12 Spectroscopy Analysis with Machine Learning Regression for the Quantification of Carbon and Nitrogen Contents in Inceptisol and Oxisol Soil Types: Comparing Different Preprocessing and Validation methods as well as Feature Importance 提出机器学习回归方法以量化土壤中碳氮含量 predictive model MAE
13 SAOT: Self-Supervised Continual Graph Learning with Structure-Aware Optimal Transport 提出SAOT框架以解决自监督持续图学习中的结构保持问题 representation learning distillation

🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)

#题目一句话要点标签🔗⭐
14 CausalMix: Data Mixture as Causal Inference for Language Model Training 提出CausalMix以解决LLM训练中的数据混合优化问题 large language model chain-of-thought
15 TiRex-2: Generalizing TiRex to Multivariate Data and Streaming 提出TiRex-2以解决多变量时间序列预测问题 foundation model
16 GSRQ: Gain-Shape Residual Quantization for Sub-1-bit KV Cache 提出GSRQ以解决KV缓存存储效率问题 large language model
17 Beyond Activation Alignment:The Alignment-Diversity Tradeoff in Task-Aware LLM Quantization 提出TASA框架以解决任务感知LLM量化中的对齐与多样性权衡问题 large language model
18 Evaluating Pretrained Music Embeddings for Cross-Performance Jazz Standard Recognition 提出基于预训练音乐嵌入的跨表演爵士标准识别方法 foundation model ✅
19 AdaBoosting Text Prompts for Vision-Language Models 提出文本提示增强方法以提升视觉语言模型的分类准确性 large language model

🔬 支柱一：机器人控制 (Robot Control) (4 篇)

#题目一句话要点标签🔗⭐
20 Valdi: Value Diffusion World Models 提出Valdi以解决动态预测在MPC中的效率问题 MPC model predictive control world model ✅
21 Local Motion Matters: A Deconstruct-Recompose Paradigm for Reinforcement Learning Pre-training from Videos 提出局部运动重要性以解决强化学习预训练效率问题 manipulation reinforcement learning policy learning
22 Language-Critique Imitation Learning from Suboptimal Demonstrations 提出语言批评框架以解决次优示范的模仿学习问题 manipulation reinforcement learning offline reinforcement learning
23 Task-Relevant Representation Decoupling for Visual Reinforcement Learning Generalization 提出任务相关表示解耦以解决视觉强化学习泛化问题 manipulation reinforcement learning

⬅️ 返回 cs.LG 首页 · 🏠 返回主页