cs.LG（2024-03-08）

📊 共 14 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) (8) 支柱九：具身大模型 (Embodied Foundation Models) (5 🔗2) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (8 篇)

#题目一句话要点标签🔗⭐
1 Unity by Diversity: Improved Representation Learning in Multimodal VAEs 提出混合专家先验以改善多模态变分自编码器的表示学习 representation learning multimodal
2 Shielded Deep Reinforcement Learning for Complex Spacecraft Tasking 提出盾牌深度强化学习以解决复杂航天任务调度问题 reinforcement learning deep reinforcement learning
3 Poly-View Contrastive Learning 提出多视角对比学习以提升表示学习效果 representation learning contrastive learning
4 Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation 提出对抗性策略优化以解决奖励过度优化问题 reinforcement learning RLHF large language model
5 Provable Multi-Party Reinforcement Learning with Diverse Human Feedback 提出多方强化学习框架以解决人类反馈多样性问题 reinforcement learning RLHF
6 Switching the Loss Reduces the Cost in Batch (Offline) Reinforcement Learning 提出FQI-log以降低批量强化学习中的样本成本 reinforcement learning
7 Simulating Battery-Powered TinyML Systems Optimised using Reinforcement Learning in Image-Based Anomaly Detection 提出基于强化学习的TinyML系统优化方案以提升电池续航 reinforcement learning
8 Reset & Distill: A Recipe for Overcoming Negative Transfer in Continual Reinforcement Learning 提出Reset & Distill以解决持续强化学习中的负迁移问题 reinforcement learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#题目一句话要点标签🔗⭐
9 A Concept-based Interpretable Model for the Diagnosis of Choroid Neoplasias using Multimodal Data 提出基于概念的可解释模型以诊断脉络膜肿瘤 multimodal
10 OmniJet-$α$: The first cross-task foundation model for particle physics 提出OmniJet-$α$以解决粒子物理跨任务建模问题 foundation model
11 Benchmarking Large Language Models for Molecule Prediction Tasks 评估大型语言模型在分子预测任务中的应用潜力 large language model ✅
12 GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM 提出GEAR以解决LLM推理中的KV缓存压缩问题 large language model ✅
13 Unfamiliar Finetuning Examples Control How Language Models Hallucinate 通过控制微调示例改善语言模型的幻觉现象 large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
14 Adversarial Sparse Teacher: Defense Against Distillation-Based Model Stealing Attacks Using Adversarial Examples 提出对抗稀疏教师模型以防御基于蒸馏的模型窃取攻击 manipulation distillation

⬅️ 返回 cs.LG 首页 · 🏠 返回主页