cs.LG（2025-06-19）

📊 共 28 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (16 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (10) 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) (16 篇)

#题目一句话要点标签🔗⭐
1 Bridging Brain with Foundation Models through Self-Supervised Learning 通过自监督学习将基础模型与脑信号分析相结合 foundation model multimodal
2 FLAME: Towards Federated Fine-Tuning Large Language Models Through Adaptive SMoE 提出FLAME框架以解决联邦学习中的资源适应性问题 large language model
3 Probing the Robustness of Large Language Models Safety to Latent Perturbations 提出激活引导攻击以增强大语言模型的安全性对抗能力 large language model ✅
4 Vision-Guided Chunking Is All You Need: Enhancing RAG with Multimodal Document Understanding 提出多模态文档分块方法以解决传统RAG系统的局限性 multimodal
5 Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights 提出Drag-and-Drop LLMs以解决大语言模型定制的高成本问题 large language model multimodal ✅
6 LazyEviction: Lagged KV Eviction with Attention Pattern Observation for Efficient Long Reasoning 提出LazyEviction以解决长推理任务中的KV缓存效率问题 large language model chain-of-thought ✅
7 Semantic Outlier Removal with Embedding Models and LLMs 提出SORE方法以解决多语言文本中冗余内容去除问题 large language model
8 A Free Probabilistic Framework for Analyzing the Transformer-based Language Models 提出自由概率框架分析基于Transformer的语言模型 large language model
9 Mr. Snuffleupagus at SemEval-2025 Task 4: Unlearning Factual Knowledge from LLMs Using Adaptive RMU 提出自适应RMU以从LLMs中去除敏感信息 large language model
10 Robust Reward Modeling via Causal Rubrics 提出Crome框架以解决奖励模型中的奖励黑客问题 large language model
11 SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity 提出SparseLoRA以加速大语言模型的微调过程 instruction following
12 Optimizing MoE Routers: Design, Implementation, and Evaluation in Transformer Models 优化MoE路由器以提升Transformer模型性能 large language model
13 The Condition Number as a Scale-Invariant Proxy for Information Encoding in Neural Units 提出KappaTune以解决神经网络信息编码效率问题 large language model
14 Next-Token Prediction Should be Ambiguity-Sensitive: A Meta-Learning Perspective 提出MetaHMM以解决高歧义下的下一个标记预测问题 foundation model
15 Can AI Dream of Unseen Galaxies? Conditional Diffusion Model for Galaxy Morphology Augmentation 提出条件扩散模型以解决天文数据稀缺问题 foundation model
16 On the Theoretical Understanding of Identifiable Sparse Autoencoders and Beyond 提出可识别稀疏自编码器以解决特征恢复问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (10 篇)

#题目一句话要点标签🔗⭐
17 CLOUD: A Scalable and Physics-Informed Foundation Model for Crystal Representation Learning 提出CLOUD模型以解决晶体属性预测的可扩展性问题 representation learning foundation model
18 Adaptive Social Metaverse Streaming based on Federated Multi-Agent Deep Reinforcement Learning 提出ASMS以解决社交元宇宙流媒体隐私与延迟问题 reinforcement learning deep reinforcement learning DRL
19 From Pixels to CSI: Distilling Latent Dynamics For Efficient Wireless Resource Management 提出一种新型机器学习方法以优化无线资源管理 reinforcement learning deep reinforcement learning latent dynamics
20 From Teacher to Student: Tracking Memorization Through Model Distillation 通过模型蒸馏降低大语言模型的记忆风险 distillation large language model
21 SlepNet: Spectral Subgraph Representation Learning for Neural Dynamics 提出SlepNet以解决图信号模式表示不足问题 representation learning spatiotemporal
22 Energy-Based Transfer for Reinforcement Learning 提出基于能量的迁移学习方法以提升强化学习效率 reinforcement learning
23 Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs 提出POST框架以解决软提示转移中的隐私与效率问题 distillation large language model
24 Distribution Parameter Actor-Critic: Shifting the Agent-Environment Boundary for Diverse Action Spaces 提出分布参数演员-评论家以解决多样化动作空间问题 reinforcement learning TD3
25 Data-Driven Policy Mapping for Safe RL-based Energy Management Systems 提出基于数据驱动的策略映射以解决安全强化学习能量管理问题 reinforcement learning policy learning
26 VRAIL: Vectorized Reward-based Attribution for Interpretable Learning 提出VRAIL框架以提升强化学习的可解释性与稳定性 reinforcement learning reward shaping

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
27 GoalLadder: Incremental Goal Discovery with Vision-Language Models 提出GoalLadder以解决视觉环境中增量目标发现问题 manipulation reinforcement learning

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

#题目一句话要点标签🔗⭐
28 Improvement of Nuclide Detection through Graph Spectroscopic Analysis Framework and its Application to Nuclear Facility Upset Detection 提出基于图谱光谱分析框架的放射性核素检测改进方法 PULSE

⬅️ 返回 cs.LG 首页 · 🏠 返回主页