cs.LG（2025-05-20）

📊 共 60 篇论文 | 🔗 14 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (30 🔗10) 支柱二：RL算法与架构 (RL & Architecture) (23 🔗2) 支柱一：机器人控制 (Robot Control) (3 🔗2) 支柱八：物理动画 (Physics-based Animation) (2) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱五：交互与反应 (Interaction & Reaction) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (30 篇)

#题目一句话要点标签🔗⭐
1 Output Scaling: YingLong-Delayed Chain of Thought in a Large Pretrained Time Series Forecasting Model 提出YingLong框架以提升时间序列预测精度 foundation model chain-of-thought ✅
2 Towards Non-Euclidean Foundation Models: Advancing AI Beyond Euclidean Frameworks 提出非欧几里得基础模型以解决现有几何框架的局限性 large language model foundation model ✅
3 KERL: Knowledge-Enhanced Personalized Recipe Recommendation using Large Language Models 提出KERL系统以解决个性化食谱推荐问题 large language model ✅
4 Foundations of Unknown-aware Machine Learning 提出未知感知学习框架以解决机器学习模型的可靠性问题 large language model foundation model multimodal
5 Quartet: Native FP4 Training Can Be Optimal for Large Language Models 提出Quartet以优化大型语言模型的FP4训练 large language model ✅
6 This Time is Different: An Observability Perspective on Time Series Foundation Models 提出Toto模型以解决多变量可观测时间序列预测问题 foundation model ✅
7 LEANCODE: Understanding Models Better for Code Simplification of Pre-trained Large Language Models 提出LeanCode以解决大规模语言模型代码简化问题 large language model
8 Table Foundation Models: on knowledge pre-training for tabular learning 提出TARTE模型以解决表格学习中的知识预训练问题 foundation model
9 LLMSynthor: Macro-Aligned Micro-Records Synthesis with Large Language Models 提出LLMSynthor以解决宏观数据与微观记录不一致问题 large language model
10 MAS-KCL: Knowledge component graph structure learning with large language model-based agentic workflow 提出MAS-KCL以优化知识组件图结构学习 large language model
11 Fusing Cross-Domain Knowledge from Multimodal Data to Solve Problems in the Physical World 提出跨域多模态数据融合框架以解决现实问题 multimodal
12 Adversarially Pretrained Transformers May Be Universally Robust In-Context Learners 提出对抗预训练变换器以解决轻量级鲁棒性问题 foundation model ✅
13 Polar Sparsity: High Throughput Batched LLM Inferencing with Scalable Contextual Sparsity 提出Polar Sparsity以解决大规模LLM推理效率问题 large language model ✅
14 The Role of Visualization in LLM-Assisted Knowledge Graph Systems: Effects on User Trust, Exploration, and Workflows 提出LinkQ以解决知识图谱探索中的用户信任问题 large language model
15 FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain 提出FisherSFT以提高语言模型的监督微调效率 large language model
16 Enhancing Learned Knowledge in LoRA Adapters Through Efficient Contrastive Decoding on Ascend NPUs 提出对比LoRA解码以提升大语言模型的任务性能 large language model
17 Spiking Neural Networks with Temporal Attention-Guided Adaptive Fusion for imbalanced Multi-modal Learning 提出时序注意力引导的自适应融合以解决多模态学习不平衡问题 multimodal
18 LLINBO: Trustworthy LLM-in-the-Loop Bayesian Optimization 提出LLINBO以解决LLM在贝叶斯优化中的不确定性问题 large language model ✅
19 ServerlessLoRA: Minimizing Latency and Cost in Serverless Inference for LoRA-Based LLMs 提出ServerlessLoRA以解决LoRA LLM推理中的延迟与成本问题 large language model
20 Interpretable Neural System Dynamics: Combining Deep Learning with System Dynamics Modeling to Support Critical Applications 提出可解释的神经系统动力学框架以解决深度学习与系统动力学的结合问题 multimodal
21 Byte Pair Encoding for Efficient Time Series Forecasting 提出基于模式的时间序列编码方法以提高预测效率 foundation model
22 Low-Cost FlashAttention with Fused Exponential and Multiplication Hardware Operators 提出融合指数与乘法运算的硬件操作以优化FlashAttention large language model
23 Scaling Law for Quantization-Aware Training 提出统一缩放法则以优化量化感知训练 large language model
24 Safety Subspaces are Not Linearly Distinct: A Fine-Tuning Case Study 研究安全子空间与线性独立性，揭示模型安全性挑战 large language model ✅
25 Acoustic and Machine Learning Methods for Speech-Based Suicide Risk Assessment: A Systematic Review 利用声学与机器学习方法评估自杀风险 multimodal
26 Quaff: Quantized Parameter-Efficient Fine-Tuning under Outlier Spatial Stability Hypothesis 提出Quaff以解决资源受限设备上LLM微调效率问题 large language model ✅
27 When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty 提出开放世界图助手以解决未标记数据的不确定性问题 large language model
28 Causes and Consequences of Representational Similarity in Machine Learning Models 探讨数据集重叠与任务重叠对模型表示相似性的影响 large language model
29 The Energy Cost of Reasoning: Analyzing Energy Usage in LLMs with Test-time Compute 提出测试时间计算以提高大语言模型的能效与准确性 large language model
30 FlowBERT: Prompt-tuned BERT for variable flow field prediction 提出FlowBERT以解决传统CFD方法计算成本高的问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (23 篇)

#题目一句话要点标签🔗⭐
31 Structured Agent Distillation for Large Language Model 提出结构化代理蒸馏以解决大语言模型压缩问题 imitation learning distillation large language model
32 Modality-Balancing Preference Optimization of Large Multimodal Models by Adversarial Negative Mining 提出多模态平衡偏好优化方法以解决模态失衡问题 preference learning large language model multimodal
33 InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language Models 提出InfiFPO以解决大语言模型融合中的偏好对齐问题 DPO direct preference optimization large language model
34 FlowQ: Energy-Guided Flow Policies for Offline Reinforcement Learning 提出FlowQ以解决离线强化学习中的指导问题 reinforcement learning offline reinforcement learning flow matching
35 Time to Embed: Unlocking Foundation Models for Time Series with Channel Descriptions 提出CHARM以解决时间序列建模的局限性问题 representation learning foundation model
36 Energy-Efficient Deep Reinforcement Learning with Spiking Transformers 提出Spike-Transformer强化学习算法以解决能耗问题 reinforcement learning deep reinforcement learning
37 AAPO: Enhancing the Reasoning Capabilities of LLMs with Advantage Momentum 提出AAPO以解决现有RL方法在推理能力提升中的低效问题 reinforcement learning PPO large language model
38 Imitation Learning via Focused Satisficing 提出聚焦满意度的模仿学习方法以提升行为接受度 reinforcement learning deep reinforcement learning imitation learning
39 The Evolution of Alpha in Finance Harnessing Human Insight and LLM Agents 提出五阶段分类法以推动金融领域的智能投资系统发展 representation learning large language model multimodal
40 Interpretable Reinforcement Learning for Load Balancing using Kolmogorov-Arnold Networks 提出Kolmogorov-Arnold网络以解决负载均衡的可解释强化学习问题 reinforcement learning PPO
41 Preference Learning with Lie Detectors can Induce Honesty or Evasion 通过谎言探测器的偏好学习提升AI系统的诚实性 preference learning DPO
42 Sample and Computationally Efficient Continuous-Time Reinforcement Learning with General Function Approximation 提出一种高效的连续时间强化学习算法以解决样本和计算效率问题 reinforcement learning
43 Text embedding models can be great data engineers 提出ADEPT以自动化数据工程管道问题 predictive model TAMP
44 TinyV: Reducing False Negatives in Verification Improves RL for LLM Reasoning 提出TinyV以解决验证器假阴性问题 reinforcement learning large language model ✅
45 Performance Optimization of Energy-Harvesting Underlay Cognitive Radio Networks Using Reinforcement Learning 提出强化学习优化能量采集下的认知无线电网络性能 reinforcement learning
46 KIPPO: Koopman-Inspired Proximal Policy Optimization 提出KIPPO以解决复杂动态环境中的策略优化问题 reinforcement learning policy learning PPO
47 Bellman operator convergence enhancements in reinforcement learning algorithms 提出贝尔曼算子改进以提升强化学习算法收敛性 reinforcement learning
48 Personalised Insulin Adjustment with Reinforcement Learning: An In-Silico Validation for People with Diabetes on Intensive Insulin Treatment 提出自适应基础-波动剂量建议系统以优化糖尿病患者胰岛素调整 reinforcement learning
49 FlowTSE: Target Speaker Extraction with Flow Matching 提出FlowTSE以解决目标说话人提取问题 flow matching
50 Self Distillation via Iterative Constructive Perturbations 提出循环优化框架以提升深度学习模型的泛化能力 distillation
51 From Reasoning to Code: GRPO Optimization for Underrepresented Languages 提出GRPO优化方法以解决小众编程语言代码生成问题 reinforcement learning large language model
52 Riemannian Flow Matching for Brain Connectivity Matrices via Pullback Geometry 提出DiffeoCFM以解决脑连接矩阵生成问题 flow matching ✅
53 When to retrain a machine learning model 提出基于不确定性的模型重训练方法以应对数据演变问题 reinforcement learning offline reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#题目一句话要点标签🔗⭐
54 RLVR-World: Training World Models with Reinforcement Learning 提出RLVR-World以优化世界模型的任务特定目标 manipulation reinforcement learning world model ✅
55 Flattening Hierarchies with Policy Bootstrapping 提出一种新算法以解决长时间目标条件强化学习中的层次性问题 locomotion manipulation reinforcement learning ✅
56 Lessons from Defending Gemini Against Indirect Prompt Injections 提出对抗性评估框架以增强Gemini模型的鲁棒性 manipulation

🔬 支柱八：物理动画 (Physics-based Animation) (2 篇)

#题目一句话要点标签🔗⭐
57 Physics-Guided Learning of Meteorological Dynamics for Weather Downscaling and Forecasting 提出PhyDL-NWP以解决传统天气预报的计算与物理不足问题 spatiotemporal
58 A PID-Controlled Tensor Wheel Decomposition Model for Dynamic Link Prediction 提出PID控制的张量轮分解模型以解决动态链接预测问题 spatiotemporal

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
59 Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models 提出文本引导向量以提升多模态大语言模型的视觉理解能力 spatial relationship large language model multimodal

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
60 Securing Transfer-Learned Networks with Reverse Homomorphic Encryption 提出一种新型同态加密方法以保护转移学习网络的训练数据 OMOMO

⬅️ 返回 cs.LG 首页 · 🏠 返回主页