cs.LG（2025-08-20）

📊 共 24 篇论文

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (15) 支柱九：具身大模型 (Embodied Foundation Models) (8) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (15 篇)

#题目一句话要点标签🔗⭐
1 Universal and Transferable Adversarial Attack on Large Language Models Using Exponentiated Gradient Descent 提出一种基于指数梯度下降的通用对抗攻击方法以增强大语言模型的鲁棒性 reinforcement learning RLHF large language model
2 PepThink-R1: LLM for Interpretable Cyclic Peptide Optimization with CoT SFT and Reinforcement Learning 提出PepThink-R1以解决循环肽优化的可解释性问题 reinforcement learning large language model chain-of-thought
3 PGF-Net: A Progressive Gated-Fusion Framework for Efficient Multimodal Sentiment Analysis 提出PGF-Net以解决多模态情感分析效率与可解释性问题 MAE multimodal
4 CuMoLoS-MAE: A Masked Autoencoder for Remote Sensing Data Reconstruction 提出CuMoLoS-MAE以解决遥感数据重建中的不确定性问题 masked autoencoder MAE
5 Aura-CAPTCHA: A Reinforcement Learning and GAN-Enhanced Multi-Modal CAPTCHA System 提出Aura-CAPTCHA以解决传统验证码易被攻破的问题 reinforcement learning large language model
6 Generative AI Against Poaching: Latent Composite Flow Matching for Wildlife Conservation 提出生成性AI方法以应对偷猎问题 flow matching spatiotemporal
7 Synthetic Adaptive Guided Embeddings (SAGE): A Novel Knowledge Distillation Method 提出SAGE以解决传统蒸馏方法的效率与泛化问题 teacher-student distillation
8 Universal Reinforcement Learning in Coalgebras: Asynchronous Stochastic Computation via Conduction 提出普适强化学习以解决异步随机计算问题 reinforcement learning
9 Kernel-based Equalized Odds: A Quantification of Accuracy-Fairness Trade-off in Fair Representation Learning 提出基于核的平衡机会准则以量化公平表示学习中的准确性与公平性权衡 representation learning
10 Graph Structure Learning with Temporal Graph Information Bottleneck for Inductive Representation Learning 提出GTGIB框架以解决动态网络中的节点表示问题 representation learning
11 Source-Guided Flow Matching 提出源引导流匹配框架以优化生成模型指导问题 flow matching
12 Federated Distillation on Edge Devices: Efficient Client-Side Filtering for Non-IID Data 提出EdgeFD以解决边缘设备上的非IID数据过滤问题 distillation
13 HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents 提出HERAKLES框架以解决开放式LLM代理的目标学习问题 reinforcement learning large language model
14 A Comparative Evaluation of Teacher-Guided Reinforcement Learning Techniques for Autonomous Cyber Operations 提出教师引导强化学习技术以提升自主网络安全操作效率 reinforcement learning
15 Beyond ReLU: Chebyshev-DQN for Enhanced Deep Q-Networks 提出Chebyshev-DQN以提升深度Q网络性能 reinforcement learning deep reinforcement learning

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

#题目一句话要点标签🔗⭐
16 Multimodal Quantum Vision Transformer for Enzyme Commission Classification from Biochemical Representations 提出多模态量子视觉变换器以解决酶功能预测问题 multimodal
17 Large Foundation Model for Ads Recommendation 提出LFM4Ads框架以解决广告推荐中的多表示转移问题 foundation model
18 Great GATsBi: Hybrid, Multimodal, Trajectory Forecasting for Bicycles using Anticipation Mechanism 提出Great GATsBi以解决自行车轨迹预测问题 multimodal
19 Evaluating Sparse Autoencoders for Monosemantic Representation 提出稀疏自编码器以解决语言模型多义性问题 large language model
20 Assessing the Quality and Security of AI-Generated Code: A Quantitative Analysis 量化评估AI生成代码的质量与安全性 large language model
21 Lossless Compression of Neural Network Components: Weights, Checkpoints, and K/V Caches in Low-Precision Formats 提出低精度格式神经网络组件无损压缩方法以降低存储成本 large language model
22 Adaptively Robust LLM Inference Optimization under Prediction Uncertainty 提出自适应鲁棒LLM推理优化算法以应对预测不确定性问题 large language model
23 Semantic Energy: Detecting LLM Hallucination Beyond Entropy 提出语义能量以解决大语言模型幻觉检测问题 large language model

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
24 DualNILM: Energy Injection Identification Enabled Disaggregation with Deep Multi-Task Learning 提出DualNILM以解决BTM能量注入对NILM的影响问题 penetration

⬅️ 返回 cs.LG 首页 · 🏠 返回主页