cs.LG（2026-07-24）

📊 共 18 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (9) 支柱二：RL算法与架构 (RL & Architecture) (8) 支柱八：物理动画 (Physics-based Animation) (1)

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

#题目一句话要点标签🔗⭐
1 Autoregressive EHR Foundation Models with Multimodal Inputs 提出多模态条件自回归模型以提升临床预测能力 foundation model multimodal
2 Phylogenetic signal in marine mammal and bird vocalizations captured by audio foundation models: the limited benefit of domain-specific pretraining 利用音频基础模型揭示海洋哺乳动物与鸟类的系统发育信号 foundation model
3 Universal BCI Personalization: One API for Frozen EEG Trunks and Foundation Models 提出Nimbus Personalizer以解决EEG个性化问题 foundation model
4 Pretraining EHR Foundation Models with Patient-Aware Sampling 提出患者感知采样方法以优化电子健康记录预训练 foundation model
5 DCS: A Unified Conditional Sensitivity Framework for Cross-Modal Copyright Infringement Detection 提出统一条件敏感性框架以解决跨模态版权侵权检测问题 foundation model multimodal
6 IFCLoRA: Topology-Aware Rank Allocation for Parameter-Efficient Fine-Tuning 提出IFCLoRA以解决LoRA方法的参数分配问题 large language model
7 Efficient Online LLM Watermark Detection via Rao-Blackwellized E-Processes 提出高效在线水印检测框架以解决LLM文本识别问题 large language model
8 Multi-Agent Debate and Visual Information Extraction for SeePhys Pro: A 1st-Place Technical Report from ICML 2026 AI4Math Track 3 Challenge 提出多代理辩论与视觉信息提取以解决物理问题 large language model
9 RIS-Kernel: A Model-Agnostic Architecture for Long-Context LLM Inference via Sparse Attention 提出RIS-Kernel以解决长上下文LLM推理中的稀疏注意力问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (8 篇)

#题目一句话要点标签🔗⭐
10 IQ-JEPA: A Joint-Embedding Predictive Architecture with a Hermitian Vision Transformer for Sound Speed and Attenuation Estimation from Ultrasound IQ Data 提出IQ-JEPA以解决超声IQ数据中的声速和衰减估计问题 JEPA Joint-Embedding Predictive Architecture joint-embedding predictive architecture
11 On the Identifiability of Controlled World Models 提出联合可识别性理论以解决受控世界模型的识别问题 world model world models JEPA
12 LunarFM: A Shared Multimodal Representation of the Moon's Surface 提出LunarFM以解决月球表面多模态数据分析问题 masked autoencoder foundation model multimodal
13 Integrated Order Dispatching and Routing for Last-Mile Pickup via Deep Reinforcement Learning 提出集成订单调度与路径规划以解决最后一公里取件问题 reinforcement learning deep reinforcement learning
14 Unbiased Open World Regularization for Fair Self-Supervised Learning 提出无偏开放世界正则化以解决自监督学习中的偏差问题 JEPA Joint-Embedding Predictive Architecture joint-embedding predictive architecture
15 Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization 提出字节前缀边际化方法以解决跨分词器蒸馏问题 distillation
16 Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning 提出MetaEvolve框架以培养自我进化的元技能 reinforcement learning
17 Indexing: the Beginning and the End 提出因果复杂性以解决深度学习中的索引问题 SSM linear attention

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

#题目一句话要点标签🔗⭐
18 Variational Low-rank Tensor Decomposition for Multisubject Spatiotemporal Data Analysis 提出时空变分低秩张量分解以解决多主体数据分析问题 spatiotemporal

⬅️ 返回 cs.LG 首页 · 🏠 返回主页