cs.LG（2023-11-02）

📊 共 19 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (10 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (6 🔗1) 支柱一：机器人控制 (Robot Control) (2) 支柱四：生成式动作 (Generative Motion) (1)

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

#题目一句话要点标签🔗⭐
1 Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models 提出离线分布鲁棒性蒸馏框架以提升视觉模型性能 distillation foundation model
2 Efficient Symbolic Policy Learning with Differentiable Symbolic Expression 提出高效符号策略学习方法以解决深度强化学习的复杂性问题 reinforcement learning deep reinforcement learning DRL
3 DreamSmooth: Improving Model-based Reinforcement Learning via Reward Smoothing 提出DreamSmooth以解决稀疏奖励预测瓶颈问题 reinforcement learning
4 A Statistical Guarantee for Representation Transfer in Multitask Imitation Learning 提出统计保证以提升多任务模仿学习中的表示转移效率 imitation learning
5 Anytime-Competitive Reinforcement Learning with Policy Prior 提出随时竞争强化学习算法以解决成本约束问题 reinforcement learning
6 Invariant Causal Imitation Learning for Generalizable Policies 提出不变因果模仿学习以解决政策泛化问题 imitation learning
7 Diffusion Models for Reinforcement Learning: A Survey 综述扩散模型在强化学习中的应用与挑战 reinforcement learning ✅
8 AI for Interpretable Chemistry: Predicting Radical Mechanistic Pathways via Contrastive Learning 提出RMechRP以解决化学反应预测的可解释性问题 contrastive learning
9 Dynamic Fair Federated Learning Based on Reinforcement Learning 提出动态公平联邦学习算法DQFFL以解决数据异质性问题 reinforcement learning
10 A Simple Solution for Offline Imitation from Observations and Examples with Possibly Incomplete Trajectories 提出TAILO以解决离线模仿学习中的不完整轨迹问题 imitation learning behavior cloning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)

#题目一句话要点标签🔗⭐
11 AWEQ: Post-Training Quantization with Activation-Weight Equalization for Large Language Models 提出AWEQ以解决大型语言模型量化效率与准确性问题 large language model
12 FlashDecoding++: Faster Large Language Model Inference on GPUs 提出FlashDecoding++以解决大语言模型推理速度问题 large language model
13 Making Harmful Behaviors Unlearnable for Large Language Models 提出可控训练框架以消除大语言模型的有害行为 large language model
14 Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game 提出Tensor Trust数据集以研究提示注入攻击问题 large language model instruction following
15 Generating QM1B with PySCF$_{\text{IPU}}$ 提出PySCF$_{ ext{IPU}}$生成QM1B数据集以推动量子化学研究 foundation model ✅
16 Resilient Multiple Choice Learning: A learned scoring scheme with application to audio scene analysis 提出弹性多重选择学习以解决音频场景分析问题 multimodal

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
17 Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learning 提出对比模块与时间注意力以解决多任务强化学习中的负迁移问题 manipulation reinforcement learning contrastive learning
18 Multi-Operational Mathematical Derivations in Latent Space 提出多操作数学推导方法以优化潜在空间表达 manipulation

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
19 Bridging the Gap: Addressing Discrepancies in Diffusion Model Training for Classifier-Free Guidance 提出更新损失函数以解决扩散模型训练中的指导不一致问题 classifier-free guidance

⬅️ 返回 cs.LG 首页 · 🏠 返回主页