cs.LG（2026-07-07）
📊 共 11 篇论文 | 🔗 1 篇有代码
🎯 兴趣领域导航
🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Canopy: A Heterograph Foundation Model for Metabolic Engineering | 提出Canopy以解决代谢工程中微生物菌株设计问题 | foundation model | ||
| 2 | X-FEMR: A Token-level Explainable Approach for Electronic Health Records Foundation Models using Transformer-based Models | 提出基于Transformer的令牌级可解释性方法以解决电子健康记录模型的黑箱问题 | foundation model | ||
| 3 | Modeling Normal Is All You Need: Joint Latent Clustering for Anomaly Detection in Multimodal Cyber-Physical Systems | 提出联合潜在聚类模型以解决多模态网络物理系统中的异常检测问题 | multimodal | ||
| 4 | Multi-Channel Spread-Spectrum Code Watermarking | 提出多通道扩频水印技术以解决代码归属问题 | large language model | ||
| 5 | No Subspace to Track: Non-Identifiability and Optimizer State in Low-Rank Training | 揭示低秩训练中的非可识别性与优化器状态问题 | large language model | ||
| 6 | Unsupervised Anomaly Detection of Information Operations Users via Behavioral and Language Patterns | 提出TENSOR以解决信息操作用户检测问题 | multimodal | ✅ |
🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 7 | Multimodal Molecular Representation Learning with Graph Neural Networks, Deep & Cross Networks, and SMILES Embeddings | 提出三分支模块融合神经网络以解决分子属性预测问题 | representation learning MAE multimodal | ||
| 8 | Strategic Bargaining in Multi-Buyer Markets: Reinforcement Learning from Verifiable Rewards for LLM Negotiations | 提出基于可验证奖励的强化学习方法以优化多买家市场谈判 | reinforcement learning large language model | ||
| 9 | FourTune: Towards Fully 4-Bit Efficient Post-Training for Diffusion Models | 提出FourTune以解决扩散模型后训练效率低下问题 | reinforcement learning distillation | ||
| 10 | Entanglement as a Structural Complexity Axis: A PAC-Bayesian View of Generalization in Quantum Policies and Value Functions | 提出PAC-Bayesian框架以揭示量子策略的泛化特性 | reinforcement learning policy learning | ||
| 11 | x-Prediction Is All You Need:Training-Free Accelerated Generation via Endpoint Decodability | 提出x-预测以解决ODE采样效率低下问题 | flow matching distillation |