cs.LG（2025-01-23）

📊 共 20 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (11 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱六：视频提取与匹配 (Video Extraction) (3 🔗1) 支柱一：机器人控制 (Robot Control) (1) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗⭐
1 Privacy-Preserving Personalized Federated Prompt Learning for Multimodal Large Language Models 提出DP-FPL，一种面向多模态LLM的差分隐私联邦Prompt学习方法 large language model multimodal
2 M3PT: A Transformer for Multimodal, Multi-Party Social Signal Prediction with Person-aware Blockwise Attention 提出M3PT：用于多模态多人社交信号预测的Transformer模型 multimodal ✅
3 Multimodal Sensor Dataset for Monitoring Older Adults Post Lower-Limb Fractures in Community Settings 发布MAISON-LLF多模态数据集，用于监测社区环境中老年人下肢骨折后的康复情况。 multimodal
4 Pilot: Building the Federated Multimodal Instruction Tuning Framework 提出Pilot联邦多模态指令调优框架，解决分布式设备上多模态大语言模型的协同微调问题。 multimodal
5 Mining Social Determinants of Health for Heart Failure Patient 30-Day Readmission via Large Language Model 利用大型语言模型挖掘社会决定因素以预测心力衰竭患者30天再入院率 large language model
6 GPT-HTree: A Decision Tree Framework Integrating Hierarchical Clustering and Large Language Models for Explainable Classification 提出GPT-HTree框架，融合分层聚类与大语言模型，实现可解释的分类。 large language model
7 OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting OSTQuant：通过正交和缩放变换优化LLM量化，提升数据分布拟合度 large language model ✅
8 Not Every AI Problem is a Data Problem: We Should Be Intentional About Data Scaling 数据规模并非解决所有AI问题的关键，应有目的地进行数据扩展 large language model
9 An Efficient Sparse Kernel Generator for O(3)-Equivariant Deep Networks 提出高效稀疏核生成器，加速O(3)-等变深度网络的Clebsch-Gordan张量积运算。 foundation model
10 Spurious Forgetting in Continual Learning of Language Models 针对语言模型持续学习中的伪遗忘，提出冻结底层参数的优化策略 large language model
11 Low-Rank Adapters Meet Neural Architecture Search for LLM Compression 结合低秩适配器与神经架构搜索，实现大语言模型高效压缩与微调 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
12 On Learning Representations for Tabular Data Distillation 提出TDColER以解决表格数据蒸馏中的特征异质性问题 representation learning distillation
13 Reinforcement Learning Platform for Adversarial Black-box Attacks with Custom Distortion Filters RLAB：基于强化学习的对抗攻击平台，支持自定义失真滤波器 reinforcement learning
14 WFCRL: A Multi-Agent Reinforcement Learning Benchmark for Wind Farm Control WFCRL：用于风电场控制的多智能体强化学习基准环境 reinforcement learning
15 MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods MambaQuant：提出方差对齐旋转量化方法，实现Mamba模型高效量化 Mamba

🔬 支柱六：视频提取与匹配 (Video Extraction) (3 篇)

#题目一句话要点标签🔗⭐
16 HumorReject: Decoupling LLM Safety from Refusal Prefix via A Little Humor HumorReject：通过幽默而非拒绝前缀提升大语言模型的安全性 HuMoR large language model ✅
17 Large Vision-Language Models for Knowledge-Grounded Data Annotation of Memes 提出ClassicMemes-50-templates数据集与知识驱动的Meme标注框架，并改进CLIP模型用于Meme-文本检索。 HuMoR
18 Sparse identification of nonlinear dynamics and Koopman operators with Shallow Recurrent Decoder Networks 提出SINDy-SHRED，通过浅层循环解码网络进行非线性动力学和Koopman算子的稀疏辨识。 sparse sensors

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
19 Utilizing Evolution Strategies to Train Transformers in Reinforcement Learning 利用进化策略训练Transformer强化学习智能体，解决复杂环境下的策略优化问题。 humanoid humanoid locomotion locomotion

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
20 One Fits All: General Mobility Trajectory Modeling via Masked Conditional Diffusion 提出GenMove：基于掩码条件扩散的通用移动轨迹建模框架 classifier-free guidance spatiotemporal

⬅️ 返回 cs.LG 首页 · 🏠 返回主页