cs.LG（2026-06-26）

📊 共 16 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) (9) 支柱九：具身大模型 (Embodied Foundation Models) (6 🔗1) 支柱四：生成式动作 (Generative Motion) (1)

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

#题目一句话要点标签🔗⭐
1 Textual Belief States for World Models: Identifiable Representation Learning Under Strict Mediation 提出文本信念状态以解决世界模型中的可识别表示学习问题 reinforcement learning world model world models
2 NormGuard: Reward-Preserving Norm Constraints in Flow-Matching Reinforcement Learning 提出NormGuard以解决流匹配强化学习中的奖励保持问题 reinforcement learning flow matching DPO
3 Are Time-Series Foundation Models Ready for E-Nose Data? An Empirical Assessment of Their Embeddings 评估时间序列基础模型在气体传感数据中的有效性 predictive model foundation model
4 RS-Diffuser: Risk-Sensitive Diffusion Planning with Distributional Value Guidance 提出RS-Diffuser以解决离线强化学习中的风险敏感规划问题 reinforcement learning policy learning offline RL
5 Disentangling Continuous-Time Latent Dynamics: Identifiability of Latent SDEs via Diffusion Shifts 通过扩散偏移提出连续时间潜在动态的可识别性方法 latent dynamics representation learning
6 PerturbCellRL: Verifier-Guided Reinforcement Learning for Single-Cell Perturbation Prediction 提出PerturbCellRL以解决单细胞干扰预测问题 reinforcement learning flow matching
7 Regularized Reward-Punishment Reinforcement Learning 提出KL耦合策略正则化以解决奖励-惩罚强化学习问题 reinforcement learning
8 Parameter Efficient Hybrid Transformer (PEHT) for Network Traffic Prediction via Dynamic Urban Congestion Integration 提出PEHT以解决动态城市网络流量预测问题 MAE multimodal
9 Learning to Reason with Curriculum II: Compositional Generalization 提出基于自适应课程学习的方法以解决组合泛化问题 reinforcement learning chain-of-thought

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

#题目一句话要点标签🔗⭐
10 HybridCodec: Modeling Discrete and Continuous Representations for Efficient Speech Language Models 提出HybridCodec以解决离散表示信息损失问题 large language model multimodal
11 LLawCo: Learning Laws of Cooperation for Modeling Embodied Multi-Agent Behavior 提出LLawCo框架以解决多智能体合作行为不一致问题 large language model
12 Dual-Learning based Penalized Multi-Align Clustering for Multi-View Incomplete and Disorderly Data 提出双学习惩罚多对齐聚类以解决多视角不完整数据问题 multimodal
13 The Weakest Link Tells It All: Outcome-Supervised Process Reward Modeling via Learnable Credit Assignment 提出LCA框架以解决过程奖励模型中的信用分配问题 large language model
14 CBD: API-Only LLM Black-Box Unlearning through Controlled Behavioral Divergence 提出CBD框架以解决API黑箱环境下的机器遗忘问题 large language model ✅
15 Continual Learning for Sequential Personalization of Small Language Models: A Stability Monitoring Analysis 提出一种稳定性监测分析方法以解决小语言模型的持续个性化问题 large language model

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
16 VGB for Masked Diffusion Model: Efficient Test-time Scaling for Reward Satisfaction and Sample Editing 提出MDM-VGB以解决生成模型的奖励优化问题 MDM

⬅️ 返回 cs.LG 首页 · 🏠 返回主页