cs.LG（2025-05-05）

📊 共 23 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) (15) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗1) 支柱一：机器人控制 (Robot Control) (1) 支柱八：物理动画 (Physics-based Animation) (1)

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

#题目一句话要点标签🔗⭐
1 SEFE: Superficial and Essential Forgetting Eliminator for Multimodal Continual Instruction Tuning 提出SEFE以解决多模态持续指令调优中的遗忘问题 large language model multimodal
2 Radio: Rate-Distortion Optimization for Large Language Model Compression 提出基于率失真优化的LLM压缩方法以解决资源限制问题 large language model
3 HSplitLoRA: A Heterogeneous Split Parameter-Efficient Fine-Tuning Framework for Large Language Models 提出HSplitLoRA以解决异构设备上大语言模型微调问题 large language model
4 Knowledge Graphs for Enhancing Large Language Models in Entity Disambiguation 利用知识图谱提升大型语言模型的实体消歧能力 large language model
5 A Note on Statistically Accurate Tabular Data Generation Using Large Language Models 提出概率驱动提示方法以提高LLM生成表格数据的统计准确性 large language model
6 Enhancing Chemical Reaction and Retrosynthesis Prediction with Large Language Model and Dual-task Learning 提出ChemDual框架以解决化学反应与逆合成预测问题 large language model
7 LLM4FTS: Enhancing Large Language Models for Financial Time Series Prediction 提出LLM4FTS框架以提升金融时间序列预测能力 large language model
8 EntroLLM: Entropy Encoded Weight Compression for Efficient Large Language Model Inference on Edge Devices 提出EntroLLM以解决边缘设备上大语言模型推理效率问题 large language model
9 Towards Cross-Modality Modeling for Time Series Analytics: A Survey in the LLM Era 提出跨模态建模方法以提升时间序列分析能力 large language model multimodal
10 RetroInfer: A Vector-Storage Approach for Scalable Long-Context LLM Inference 提出RetroInfer以解决长上下文LLM推理效率问题 large language model
11 Towards Quantifying the Hessian Structure of Neural Networks 揭示神经网络Hessian矩阵的近块对角结构 large language model
12 When Your Own Output Becomes Your Training Data: Noise-to-Meaning Loops and a Formal RSI Trigger 提出噪声到意义的递归自我改进模型以提升AI复杂性 large language model
13 Less is More: Efficient Weight Farcasting with 1-Layer Neural Network 提出高效的1层神经网络权重远预测方法以解决训练效率问题 large language model
14 Unlearning vs. Obfuscation: Are We Truly Removing Knowledge? 提出DF-MCQ以解决知识移除的有效性问题 large language model
15 Rewriting Pre-Training Data Boosts LLM Performance in Math and Code 通过重写预训练数据提升大语言模型在数学和代码生成中的表现 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
16 Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL 提出GVM-RAFT以优化链式推理模型的梯度方差 reinforcement learning large language model chain-of-thought ✅
17 Transfer learning-enhanced deep reinforcement learning for aerodynamic airfoil optimisation subject to structural constraints 提出基于迁移学习的深度强化学习方法以优化气动翼型 reinforcement learning deep reinforcement learning DRL
18 Graph Neural Network-Based Reinforcement Learning for Controlling Biological Networks - the GATTACA Framework 提出GATTACA框架以解决生物网络控制问题 reinforcement learning deep reinforcement learning DRL
19 GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds 提出GeoERM以解决多任务学习中的几何不一致问题 representation learning
20 T2S: High-resolution Time Series Generation with Text-to-Series Diffusion Models 提出T2S框架以解决时间序列生成中的数据稀疏与不平衡问题 flow matching multimodal
21 Optimizing LLMs for Resource-Constrained Environments: A Survey of Model Compression Techniques 综述模型压缩技术以优化资源受限环境中的LLM distillation large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
22 A New Perspective To Understanding Multi-resolution Hash Encoding For Neural Fields 提出领域操控的新视角以理解多分辨率哈希编码 manipulation

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

#题目一句话要点标签🔗⭐
23 Enabling Local Neural Operators to perform Equation-Free System-Level Analysis 提出局部神经算子以实现无方程系统级分析 spatiotemporal

⬅️ 返回 cs.LG 首页 · 🏠 返回主页