cs.LG（2024-02-21）

📊 共 26 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (12) 支柱二：RL算法与架构 (RL & Architecture) (10 🔗2) 支柱一：机器人控制 (Robot Control) (3 🔗1) 支柱五：交互与反应 (Interaction & Reaction) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#题目一句话要点标签🔗⭐
1 PQA: Zero-shot Protein Question Answering for Free-form Scientific Enquiry with Large Language Models 提出零-shot蛋白质问答系统以解决现有方法的局限性 large language model multimodal
2 An Explainable Transformer-based Model for Phishing Email Detection: A Large Language Model Approach 提出基于Transformer的模型以解决网络钓鱼邮件检测问题 large language model
3 APTQ: Attention-aware Post-Training Mixed-Precision Quantization for Large Language Models 提出APTQ以解决大语言模型的量化部署问题 large language model
4 FinGPT-HPC: Efficient Pretraining and Finetuning Large Language Models for Financial Applications with High-Performance Computing 提出FinGPT-HPC以高效预训练和微调金融领域的大型语言模型 large language model
5 ProSparse: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Models 提出ProSparse以提升大语言模型的激活稀疏性 large language model
6 Recursive Speculative Decoding: Accelerating LLM Inference via Sampling Without Replacement 提出递归推测解码以解决LLM推理加速问题 large language model
7 Diet-ODIN: A Novel Framework for Opioid Misuse Detection with Interpretable Dietary Patterns 提出Diet-ODIN框架以解决阿片类药物滥用检测问题 large language model
8 Motion Code: Robust Time Series Classification and Forecasting via Sparse Variational Multi-Stochastic Processes Learning 提出Motion Code以解决噪声数据下的时间序列分类与预测问题 TAMP
9 Coercing LLMs to do and reveal (almost) anything 提出多种攻击方法以揭示大型语言模型的脆弱性 large language model
10 Do Efficient Transformers Really Save Computation? 探讨高效Transformer的计算效率与适用性 chain-of-thought
11 ProPD: Dynamic Token Tree Pruning and Generation for LLM Parallel Decoding 提出ProPD以解决LLM并行解码效率问题 large language model
12 STENCIL: Submodular Mutual Information Based Weak Supervision for Cold-Start Active Learning 提出STENCIL以解决冷启动主动学习中的类不平衡问题 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🔗⭐
13 PaCKD: Pattern-Clustered Knowledge Distillation for Compressing Memory Access Prediction Models 提出PaCKD以压缩内存访问预测模型并提升性能 distillation
14 FLD: Fourier Latent Dynamics for Structured Motion Representation and Learning 提出FLD方法以解决运动轨迹稀疏问题 latent dynamics motion representation
15 UniGraph: Learning a Unified Cross-Domain Foundation Model for Text-Attributed Graphs 提出UniGraph以解决跨领域图学习的知识迁移问题 representation learning large language model foundation model
16 Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future Directions 系统评估深度生成模型在离线策略学习中的应用 reinforcement learning policy learning offline RL ✅
17 Wisdom of Committee: Distilling from Foundation Model to Specialized Application Model 提出教学委员会以解决基础模型与专用模型间的知识转移问题 distillation foundation model
18 The Effect of Batch Size on Contrastive Self-Supervised Speech Representation Learning 研究批量大小对对比自监督语音表示学习的影响 representation learning foundation model ✅
19 Contextual Molecule Representation Learning from Chemical Reaction Knowledge 提出REMO框架以解决分子表示学习中的复杂性问题 representation learning ReMoS
20 AttackGNN: Red-Teaming GNNs in Hardware Security Using Reinforcement Learning 提出AttackGNN以评估GNN在硬件安全中的鲁棒性 reinforcement learning
21 Enhancing Reinforcement Learning Agents with Local Guides 提出局部引导策略以增强强化学习代理的性能 reinforcement learning
22 DiffPLF: A Conditional Diffusion Model for Probabilistic Forecasting of EV Charging Load 提出DiffPLF以解决电动汽车充电负荷预测问题 MAE penetration

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#题目一句话要点标签🔗⭐
23 Learning to Poison Large Language Models for Downstream Manipulation 提出梯度引导的后门触发器学习以解决大语言模型的数据中毒问题 manipulation large language model
24 Corrective Machine Unlearning 提出纠正性机器遗忘以应对数据完整性挑战 manipulation ✅
25 Stealthy Adversarial Attacks on Stochastic Multi-Armed Bandits 提出隐蔽性对抗攻击以解决随机多臂老虎机的安全问题 manipulation

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

#题目一句话要点标签🔗⭐
26 DSLR: Diversity Enhancement and Structure Learning for Rehearsal-based Graph Continual Learning 提出DSLR以解决图持续学习中的重放缓冲区问题 CHOIS ✅

⬅️ 返回 cs.LG 首页 · 🏠 返回主页