cs.LG(2024-02-13)

📊 共 21 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱二:RL算法与架构 (RL & Architecture) (9) 支柱九:具身大模型 (Embodied Foundation Models) (5 🔗2) 支柱一:机器人控制 (Robot Control) (2) 支柱八:物理动画 (Physics-based Animation) (2 🔗1) 支柱五:交互与反应 (Interaction & Reaction) (1) 支柱七:动作重定向 (Motion Retargeting) (1) 支柱四:生成式动作 (Generative Motion) (1)

🔬 支柱二:RL算法与架构 (RL & Architecture) (9 篇)

#题目一句话要点标签🔗
1 Graph Mamba: Towards Learning on Graphs with State Space Models 提出Graph Mamba以解决图神经网络的长距离依赖问题 Mamba SSM state space model
2 Hybrid Inverse Reinforcement Learning 提出混合逆强化学习以提高样本效率 reinforcement learning imitation learning inverse reinforcement learning
3 Rethinking Machine Unlearning for Large Language Models 提出大语言模型去学习方法以消除不良数据影响 reinforcement learning large language model
4 Deep Reinforcement Learning for Controlled Traversing of the Attractor Landscape of Boolean Models in the Context of Cellular Reprogramming 提出深度强化学习框架以优化细胞重编程策略 reinforcement learning deep reinforcement learning
5 World Model on Million-Length Video And Language With Blockwise RingAttention 提出基于块状环注意力的模型以解决长视频和语言理解问题 world model world models
6 Conservative and Risk-Aware Offline Multi-Agent Reinforcement Learning 提出离线多智能体强化学习方案以解决环境不确定性问题 reinforcement learning conservative q-learning
7 PRDP: Proximal Reward Difference Prediction for Large-Scale Reward Finetuning of Diffusion Models 提出PRDP以解决视觉领域大规模奖励微调问题 reinforcement learning foundation model
8 Provable Traffic Rule Compliance in Safe Reinforcement Learning on the Open Sea 提出基于时序逻辑的强化学习方法以确保海上交通规则合规性 reinforcement learning
9 Disambiguated Node Classification with Graph Neural Networks 提出一种新方法以解决图神经网络中的模糊节点分类问题 representation learning contrastive learning

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

#题目一句话要点标签🔗
10 COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability 提出COLD-Attack以解决可控性与隐蔽性问题 large language model
11 The dynamic interplay between in-context and in-weight learning in humans and neural networks 提出动态交互模型以解决人类与神经网络学习的双重性问题 large language model
12 Can LLMs Learn New Concepts Incrementally without Forgetting? 提出Concept-1K数据集以解决LLMs增量学习遗忘问题 large language model
13 Unsupervised Evaluation of Code LLMs with Round-Trip Correctness 提出回环正确性评估方法以解决代码LLM评估问题 large language model
14 LLaGA: Large Language and Graph Assistant 提出LLaGA以解决图结构数据分析中的语言模型应用挑战 large language model

🔬 支柱一:机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗
15 Bayesian Strategic Classification 提出部分信息释放策略以优化分类器准确性 manipulation
16 The Effect of Data Poisoning on Counterfactual Explanations 研究数据中毒对反事实解释的影响 manipulation

🔬 支柱八:物理动画 (Physics-based Animation) (2 篇)

#题目一句话要点标签🔗
17 A Convergence Analysis of Approximate Message Passing with Non-Separable Functions and Applications to Multi-Class Classification 提出对近似消息传递的收敛性分析以解决多类分类问题 AMP
18 Gaussian Ensemble Belief Propagation for Efficient Inference in High-Dimensional Systems 提出高斯集成信念传播算法以解决高维推理问题 spatiotemporal

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

#题目一句话要点标签🔗
19 Homomorphism Counts for Graph Neural Networks: All About That Basis 提出基于同态计数的图神经网络以提升表达能力 OMOMO

🔬 支柱七:动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗
20 Approximately Piecewise E(3) Equivariant Point Networks 提出APEN框架以解决点云网络的E(3)对称性问题 human motion

🔬 支柱四:生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗
21 ROSpace: Intrusion Detection Dataset for a ROS2-Based Cyber-Physical System 提出ROS2基础的入侵检测数据集以解决现有数据集不足问题 penetration

⬅️ 返回 cs.LG 首页 · 🏠 返回主页