cs.LG（2026-01-16）

📊 共 23 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (9 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (8) 支柱一：机器人控制 (Robot Control) (4) 支柱四：生成式动作 (Generative Motion) (2)

🔬 支柱二：RL算法与架构 (RL & Architecture) (9 篇)

#题目一句话要点标签🔗⭐
1 Backdoor Attacks on Multi-modal Contrastive Learning 多模态对比学习中的后门攻击综述与分析 representation learning contrastive learning multimodal
2 Offline Reinforcement-Learning-Based Power Control for Application-Agnostic Energy Efficiency 提出基于离线强化学习的CPU功耗控制方法，提升并行应用能效。 reinforcement learning offline RL offline reinforcement learning
3 Factored Value Functions for Graph-Based Multi-Agent Reinforcement Learning 提出扩散价值函数（DVF）用于解决图结构多智能体强化学习中的信用分配问题 reinforcement learning
4 Information Theoretic Perspective on Representation Learning 提出信息论框架，分析回归任务中最后一层嵌入表示的学习。 representation learning
5 Latent Dynamics Graph Convolutional Networks for model order reduction of parameterized time-dependent PDEs 提出LD-GCN用于参数化时变偏微分方程的降阶模型，提升可解释性和时间外推能力 latent dynamics ✅
6 AVP-Pro: An Adaptive Multi-Modal Fusion and Contrastive Learning Approach for Comprehensive Two-Stage Antiviral Peptide Identification AVP-Pro：一种自适应多模态融合与对比学习方法，用于全面的两阶段抗病毒肽识别 contrastive learning
7 Combating Spurious Correlations in Graph Interpretability via Self-Reflection 提出基于自反思的图解释性方法，提升在虚假相关性图上的性能 representation learning large language model
8 Reasoning Distillation for Lightweight Automated Program Repair 提出基于推理蒸馏的轻量级自动化程序修复方法，提升模型性能。 distillation
9 Model-free policy gradient for discrete-time mean-field control 提出MF-REINFORCE算法，解决离散时间平均场控制中的无模型策略梯度学习问题 reinforcement learning policy learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (8 篇)

#题目一句话要点标签🔗⭐
10 FORESTLLM: Large Language Models Make Random Forest Great on Few-shot Tabular Learning FORESTLLM：利用大语言模型提升随机森林在少样本表格数据学习中的性能 large language model
11 Differentially Private Subspace Fine-Tuning for Large Language Models 提出DP-SFT，通过差分隐私子空间微调提升大语言模型隐私保护下的性能。 large language model
12 FAQ: Mitigating Quantization Error via Regenerating Calibration Data with Family-Aware Quantization FAQ：通过家族感知量化再生校准数据，缓解量化误差 large language model chain-of-thought
13 Unlocking the Potentials of Retrieval-Augmented Generation for Diffusion Language Models 提出SPREAD框架，解决检索增强扩散语言模型中的语义漂移问题 large language model
14 Scalable Music Cover Retrieval Using Lyrics-Aligned Audio Embeddings 提出LIVI：利用歌词对齐音频嵌入实现可扩展的音乐翻唱检索 multimodal
15 SDFLoRA: Selective Dual-Module LoRA for Federated Fine-tuning with Heterogeneous Clients SDFLoRA：用于异构客户端联邦微调的选择性双模块LoRA large language model
16 Optimized Algorithms for Text Clustering with LLM-Generated Constraints 提出基于LLM生成约束的文本聚类优化算法，显著降低资源消耗。 large language model
17 HOSL: Hybrid-Order Split Learning for Memory-Constrained Edge Training 提出HOSL以解决边缘设备内存受限的训练问题 large language model

🔬 支柱一：机器人控制 (Robot Control) (4 篇)

#题目一句话要点标签🔗⭐
18 Knowledge is Not Enough: Injecting RL Skills for Continual Adaptation 提出PaST框架，通过注入强化学习技能向量实现LLM的持续知识适应 manipulation reinforcement learning large language model
19 Toward Adaptive Grid Resilience: A Gradient-Free Meta-RL Framework for Critical Load Restoration 提出基于无梯度元强化学习的自适应电网恢复框架，提升关键负荷恢复能力。 model predictive control reinforcement learning
20 QUPID: A Partitioned Quantum Neural Network for Anomaly Detection in Smart Grid 提出QUPID：一种用于智能电网异常检测的分区量子神经网络 manipulation
21 IMS: Intelligent Hardware Monitoring System for Secure SoCs 提出基于神经网络的硬件监控系统IMS，用于保障SoC中AXI总线的安全 manipulation

🔬 支柱四：生成式动作 (Generative Motion) (2 篇)

#题目一句话要点标签🔗⭐
22 GenDA: Generative Data Assimilation on Complex Urban Areas via Classifier-Free Diffusion Guidance 提出GenDA框架以解决城市风流重建问题 classifier-free guidance sparse sensors
23 TimeMar: Multi-Scale Autoregressive Modeling for Unconditional Time Series Generation TimeMar：提出一种多尺度自回归模型用于无条件时间序列生成。 VQ-VAE

⬅️ 返回 cs.LG 首页 · 🏠 返回主页