cs.LG（2023-10-11）

📊 共 22 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (11 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (8 🔗4) 支柱一：机器人控制 (Robot Control) (3)

🔬 支柱二：RL算法与架构 (RL & Architecture) (11 篇)

#题目一句话要点标签🔗⭐
1 Large Language Models Are Zero-Shot Time Series Forecasters 提出将时间序列预测转化为文本生成的零-shot方法 RLHF large language model multimodal
2 From Supervised to Generative: A Novel Paradigm for Tabular Deep Learning with Large Language Models 提出生成性表格学习框架以解决传统表格深度学习的局限性 predictive model large language model foundation model ✅
3 Linear Latent World Models in Simple Transformers: A Case Study on Othello-GPT 提出线性潜在世界模型以增强Othello-GPT的决策能力 world model world models foundation model
4 Deep Reinforcement Learning for Autonomous Cyber Defence: A Survey 综述深度强化学习在自主网络防御中的应用与挑战 reinforcement learning deep reinforcement learning DRL
5 Accountability in Offline Reinforcement Learning: Explaining Decisions with a Corpus of Examples 提出可问责的离线控制器以解决医疗决策透明性问题 reinforcement learning offline reinforcement learning
6 Contextualized Policy Recovery: Modeling and Interpreting Medical Decisions with Adaptive Imitation Learning 提出上下文化政策恢复方法以解决医疗决策可解释性问题 policy learning imitation learning
7 Self-supervised Representation Learning From Random Data Projectors 提出一种无监督表示学习方法以解决数据增强依赖问题 representation learning
8 Survey on Imbalanced Data, Representation Learning and SEP Forecasting 提出表征学习以解决不平衡数据问题 representation learning
9 Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages 提出自适应重放比以解决视觉强化学习中的可塑性损失问题 reinforcement learning
10 Robust Safe Reinforcement Learning under Adversarial Disturbances 提出鲁棒安全强化学习框架以应对外部干扰问题 reinforcement learning
11 Imitation Learning from Purified Demonstrations 提出通过扩散过程净化示范以解决模仿学习中的噪声问题 imitation learning

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

#题目一句话要点标签🔗⭐
12 LLark: A Multimodal Instruction-Following Language Model for Music 提出LLark以解决音乐理解中的多模态指令跟随问题 multimodal instruction following ✅
13 Risk Aware Benchmarking of Large Language Models 提出风险意识基准测试框架以评估大型语言模型的社会技术风险 large language model foundation model
14 The Expressive Power of Transformers with Chain of Thought 提出链式思维提升变换器推理能力 chain-of-thought
15 Hypercomplex Multimodal Emotion Recognition from EEG and Peripheral Physiological Signals 提出超复数多模态网络以解决情感识别的不足问题 multimodal ✅
16 CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving 提出CacheGen以解决长上下文处理延迟问题 large language model ✅
17 D2 Pruning: Message Passing for Balancing Diversity and Difficulty in Data Pruning 提出D2 Pruning以平衡数据剪枝中的多样性与难度问题 multimodal
18 MatFormer: Nested Transformer for Elastic Inference 提出MatFormer以解决弹性推理问题 foundation model ✅
19 In-Context Unlearning: Language Models as Few Shot Unlearners 提出上下文去学习方法以解决大语言模型的去学习问题 large language model

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#题目一句话要点标签🔗⭐
20 COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL 提出COPlanner以解决模型预测误差导致的次优策略问题 MPC model predictive control reinforcement learning
21 Score Regularized Policy Optimization through Diffusion Behavior 提出高效的确定性推理策略以解决扩散模型采样慢的问题 locomotion reinforcement learning offline reinforcement learning
22 First-Order Dynamic Optimization for Streaming Convex Costs 提出首阶动态优化算法以解决流式凸成本问题 model predictive control

⬅️ 返回 cs.LG 首页 · 🏠 返回主页