cs.LG(2024-02-07)

📊 共 32 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) (17 🔗3) 支柱九:具身大模型 (Embodied Foundation Models) (13 🔗1) 支柱三:空间感知与语义 (Perception & Semantics) (1 🔗1) 支柱八:物理动画 (Physics-based Animation) (1)

🔬 支柱二:RL算法与架构 (RL & Architecture) (17 篇)

#题目一句话要点标签🔗
1 A Primal-Dual Algorithm for Offline Constrained Reinforcement Learning with Linear MDPs 提出一种原始对偶算法以解决线性MDP的离线强化学习问题 reinforcement learning offline RL offline reinforcement learning
2 Interactive Symbolic Regression through Offline Reinforcement Learning: A Co-Design Framework 提出Symbolic Q-network以解决符号回归中的专家知识整合问题 reinforcement learning offline reinforcement learning IMoS
3 Compressing Deep Reinforcement Learning Networks with a Dynamic Structured Pruning Method for Autonomous Driving 提出动态结构化剪枝方法以压缩深度强化学习网络 reinforcement learning deep reinforcement learning DRL
4 Do Transformer World Models Give Better Policy Gradients? 提出动作世界模型以优化长时间跨度的策略梯度 reinforcement learning world model world models
5 Analyzing Adversarial Inputs in Deep Reinforcement Learning 提出对抗输入分析框架以提升深度强化学习的安全性 reinforcement learning deep reinforcement learning DRL
6 Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Design 提出离散流模型以解决多模态生成问题 flow matching multimodal
7 Multi-Patch Prediction: Adapting LLMs for Time Series Representation Learning 提出aLLM4TS框架以解决时间序列表示学习问题 representation learning contrastive learning large language model
8 Learning by Doing: An Online Causal Reinforcement Learning Framework with Causal-Aware Policy 提出在线因果强化学习框架以提升决策可解释性 reinforcement learning policy learning
9 OIL-AD: An Anomaly Detection Framework for Sequential Decision Sequences 提出OIL-AD框架以解决决策序列中的异常检测问题 reinforcement learning imitation learning transformer policy
10 Group Distributionally Robust Dataset Distillation with Risk Minimization 提出基于风险最小化的群体分布鲁棒数据集蒸馏方法 distillation
11 Causal Representation Learning from Multiple Distributions: A General Setting 提出一种非参数方法以解决多分布下的因果表示学习问题 representation learning
12 A Masked language model for multi-source EHR trajectories contextual representation learning 提出基于掩码语言模型的多源电子健康记录轨迹表示学习方法 representation learning
13 On Provable Length and Compositional Generalization 提出可证明的长度与组合泛化方法以解决序列模型的泛化问题 state space model chain-of-thought
14 Code as Reward: Empowering Reinforcement Learning with VLMs 提出VLM-CaR框架以解决强化学习中的奖励计算问题 reinforcement learning
15 Online Cascade Learning for Efficient Inference over Streams 提出在线级联学习以解决大语言模型推理效率问题 imitation learning large language model
16 Convergence of Natural Policy Gradient for a Family of Infinite-State Queueing MDPs 提出自然策略梯度算法以解决无限状态队列MDP收敛问题 reinforcement learning PPO
17 Latent Plan Transformer for Trajectory Abstraction: Planning as Latent Space Inference 提出潜在计划变换器以解决长远规划问题 reinforcement learning offline reinforcement learning

🔬 支柱九:具身大模型 (Embodied Foundation Models) (13 篇)

#题目一句话要点标签🔗
18 The Fine-Grained Complexity of Gradient Computation for Training Large Language Models 提出细粒度复杂度分析以优化大语言模型训练 large language model
19 De-amplifying Bias from Differential Privacy in Language Model Fine-tuning 提出反偏见方法以解决差分隐私在语言模型微调中的问题 large language model
20 Examining Modality Incongruity in Multimodal Federated Learning for Medical Vision and Language-based Disease Detection 提出多模态联邦学习以解决模态不一致问题 multimodal
21 Learning on Multimodal Graphs: A Survey 综述多模态图学习技术以推动AI应用发展 multimodal
22 L4Q: Parameter Efficient Quantization-Aware Fine-Tuning on Large Language Models 提出L4Q以解决大语言模型的量化与微调问题 large language model
23 CrashFormer: A Multimodal Architecture to Predict the Risk of Crash 提出CrashFormer以解决交通事故预测问题 multimodal
24 ApiQ: Finetuning of 2-Bit Quantized Large Language Model 提出ApiQ以解决大语言模型量化微调中的信息丢失问题 large language model
25 Opening the AI black box: program synthesis via mechanistic interpretability 提出MIPS方法以实现神经网络的程序合成 large language model
26 Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications 通过剪枝和低秩修改评估安全对齐的脆弱性 large language model
27 Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation 提出DOMINO算法以解决LLMs生成约束问题 large language model
28 LEVI: Generalizable Fine-tuning via Layer-wise Ensemble of Different Views 提出LEVI以解决OOD泛化问题 foundation model
29 An Artificial Intelligence (AI) workflow for catalyst design and optimization 提出AI工作流程以优化催化剂设计应对环境与能源挑战 large language model
30 SumRec: A Framework for Recommendation using Open-Domain Dialogue 提出SumRec框架以利用开放域对话进行推荐 large language model

🔬 支柱三:空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗
31 Open-Vocabulary Calibration for Fine-tuned CLIP 提出距离感知校准方法以解决细调CLIP模型的置信度校准问题 open-vocabulary open vocabulary

🔬 支柱八:物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗
32 A New Method for Sensorless Estimation of the Speed and Position in Brushed DC Motors Using Support Vector Machines 提出基于支持向量机的无传感器直流电机速度与位置估计方法 PULSE

⬅️ 返回 cs.LG 首页 · 🏠 返回主页