cs.LG（2026-08-06）

📊 共 33 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (15 🔗3) 支柱九：具身大模型 (Embodied Foundation Models) (15 🔗3) 支柱一：机器人控制 (Robot Control) (2) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (15 篇)

#题目一句话要点标签🔗⭐
1 RxnCLF: Contrastive Transformation-Aware Reaction Foundation Model for Improved Reactivity Prediction 提出RxnCLF以解决反应产率预测难题 representation learning contrastive learning foundation model
2 BioM-JEPA: joint-embedding prediction of graph-connected gene blocks in single cells 提出BioM-JEPA以解决单细胞基因块预测问题 JEPA Joint-Embedding Predictive Architecture joint-embedding predictive architecture
3 Does Latent Context Help? A Controlled Evaluation of Inverse Reinforcement Learning in Arctic Shipping 评估潜在上下文对反向强化学习在北极航运中的帮助 reinforcement learning inverse reinforcement learning
4 BioKD: Selective Physiology-to-Video Knowledge Distillation via Reliability Gate for Emotion Recognition 提出BioKD以解决模糊行为线索下的情感识别问题 distillation privileged information multimodal
5 On-Policy Self-Distillation without Any Supervision 提出无监督的在线自蒸馏方法以提升模型性能 distillation large language model
6 ProDVI: Programmatic Dynamics Priors for Value Network Initialization 提出ProDVI以解决深度强化学习样本效率低下问题 reinforcement learning deep reinforcement learning large language model
7 RRC: Unlocking Generative Reward Models in LLM Reinforcement Learning via Ranking-Based Reward Construction 提出RRC方法以解决生成奖励模型在强化学习中的应用问题 reinforcement learning ✅
8 Stochastic Dynamics on Persistence Diagram Space via Reinforcement Learning 提出强化学习框架以实现持久性图的随机动态演化 reinforcement learning
9 SAGA: Score-Weighted Adaptive Generation Alignment for Low-Resource Nordic Language Models 提出SAGA框架以解决低资源北欧语言模型的偏好优化问题 DPO large language model
10 Hybrid-Adaptive Thread Tuning to Mitigate Simulation Execution Bottlenecks in High-Performance Reinforcement Learning Inference 提出AutoThread以解决高性能强化学习推理中的仿真执行瓶颈问题 reinforcement learning ✅
11 Flowing Through States: Neural ODE Regularization for Reinforcement Learning 提出神经ODE正则化以解决强化学习中的状态表示问题 reinforcement learning PPO latent dynamics
12 Game-Theoretic Inverse Reinforcement Learning for Modeling Competitive Human Driving: A Cut-in Prediction Study 提出博弈论逆强化学习以解决竞争性人类驾驶建模问题 reinforcement learning inverse reinforcement learning
13 Retrofitting Linear Attention into Diffusion Language Models 提出块混合注意力以加速扩散语言模型推理 linear attention ✅
14 CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction 提出CrystalGRPO以解决晶体结构预测中的目标对齐与覆盖问题 reinforcement learning
15 FedTransKD-IDS: Robust Federated Transfer Learning with Knowledge Distillation for Intrusion Detection in IoT 提出FedTransKD-IDS以解决物联网入侵检测中的隐私与效率问题 distillation

🔬 支柱九：具身大模型 (Embodied Foundation Models) (15 篇)

#题目一句话要点标签🔗⭐
16 MetaboLLM: a metabolomics-specialized large language model for biochemical knowledge integration and predictive metabolite graph construction 提出MetaboLLM以解决代谢组学知识整合与预测问题 large language model
17 A Six-Dimensional Taxonomy of Post-Training Adaptation Techniques with Applications in AI Governance 提出六维分类法以整合后训练适应技术 large language model foundation model multimodal
18 SkillTFM: Gated Skill Evolution for Training-Free Adaptation of Tabular Foundation Models 提出SkillTFM以解决表格基础模型适应性不足问题 foundation model
19 Do Tabular Foundation Models Agree with Themselves? 提出对表格基础模型一致性的新评估方法 foundation model
20 GAUGE: Granularity-Adaptive Counterfactual Gating of Evidence for Incomplete Multimodal Classification 提出GAUGE以解决多模态分类中的不完整性问题 multimodal
21 LLM Inference Under Bursty Workload Distribution: Modifying the WAIT Algorithm 提出轻量级WAIT算法扩展以应对突发工作负载问题 large language model
22 GROM: Gradient-Free Rapid One-Shot Machine Unlearning 提出GROM以解决机器遗忘效率低下问题 large language model ✅
23 CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits 提出CircuitSteer以解决大语言模型行为控制问题 large language model ✅
24 How Much Reconstruction Does Quantum Machine Learning Need? Late Fusion of Independently Trained Quantum Subcircuits 提出晚融合方法以降低量子机器学习的重构成本 multimodal
25 Align-RAG: Alignment Is All You Need for TSFM In-Context Learning 提出Align-RAG以优化时间序列模型的检索增强预测 foundation model ✅
26 Bootstrap-Conditioned Action Selection with Tabular Foundation Models 提出BC-ICL以解决稀疏交互数据下的个性化决策问题 foundation model
27 CertBind from Multimodal Connectivity to Certifiable Retrieval Decisions 提出CertBind以解决多模态连接的可证实检索决策问题 multimodal
28 The Sparsity Whisperer 提出差异感知剪枝方法以提升大语言模型的推理效率 large language model
29 Quantization Damage Is Multiplicative, Not Additive 提出量化损伤乘法模型以解决语言模型决策不确定性问题 large language model
30 Cascade: Exploiting SLO-Aware latency budget for fair and high goodput LLM inference serving 提出Cascade以解决LLM推理服务中的延迟预算问题 large language model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
31 Observation-Grounded Self-Predictive Reinforcement Learning for Visual Continuous Control 提出观察基础自预测强化学习以解决视觉连续控制问题 humanoid reinforcement learning policy learning
32 Behavioral Residualization for Unsupervised Intrusion Detection in Automotive CAN Networks 提出行为残差化方法以解决汽车CAN网络的无监督入侵检测问题 manipulation

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

#题目一句话要点标签🔗⭐
33 Provably Efficient Self-Calibrating Quantum Fault Tolerance 提出自校准量子容错方法以解决持续校准问题 PULSE

⬅️ 返回 cs.LG 首页 · 🏠 返回主页