cs.LG（2024-02-02）

📊 共 37 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (23 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (12 🔗2) 支柱五：交互与反应 (Interaction & Reaction) (1) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (23 篇)

#题目一句话要点标签🔗⭐
1 Chameleon: Foundation Models for Fairness-aware Multi-modal Data Augmentation to Enhance Coverage of Minorities 提出Chameleon以解决多模态数据中少数群体覆盖不足问题 large language model foundation model
2 A Survey for Foundation Models in Autonomous Driving 综述基础模型在自动驾驶中的应用与挑战 large language model foundation model
3 Large Language Models for Time Series: A Survey 提出大语言模型分析时间序列数据的方法以解决跨领域挑战 large language model multimodal
4 Explaining latent representations of generative models with large multimodal models 提出框架以解释生成模型的潜在表示 multimodal
5 Sample, estimate, aggregate: A recipe for causal discovery foundation models 提出基于基础模型的因果发现方法以应对数据限制问题 foundation model
6 On Catastrophic Inheritance of Large Foundation Models 提出UIM框架以解决大型基础模型的灾难性继承问题 foundation model
7 Large Language Model Agent for Hyper-Parameter Optimization 提出AgentHPO以解决超参数优化效率低下问题 large language model
8 InferCept: Efficient Intercept Support for Augmented Large Language Model Inference 提出InferCept以解决LLM推理中的资源浪费问题 large language model
9 Leveraging Large Language Models for Structure Learning in Prompted Weak Supervision 提出结构优化模块以解决弱监督学习中的依赖结构问题 large language model ✅
10 Parametric Feature Transfer: One-shot Federated Learning with Foundation Models 提出FedPFT以解决一轮联邦学习中的准确性与通信效率问题 foundation model
11 Position Paper: Assessing Robustness, Privacy, and Fairness in Federated Learning Integrated with Foundation Models 提出联邦学习与基础模型集成以解决鲁棒性、隐私和公平性问题 foundation model
12 Human-like Category Learning by Injecting Ecological Priors from Large Language Models into Neural Networks 通过注入生态先验提升神经网络的人类类类别学习能力 large language model
13 Integrating Large Language Models in Causal Discovery: A Statistical Causal Approach 提出统计因果提示以整合大语言模型于因果发现 large language model
14 From Words to Molecules: A Survey of Large Language Models in Chemistry 探讨大语言模型在化学领域的应用与挑战 large language model
15 Can MLLMs Perform Text-to-Image In-Context Learning? 提出T2I-ICL基准数据集以解决多模态学习挑战 large language model multimodal chain-of-thought ✅
16 Efficient Causal Graph Discovery Using Large Language Models 提出基于大语言模型的高效因果图发现方法 large language model
17 Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack 提出Vaccine以解决大语言模型的有害微调攻击问题 large language model ✅
18 Stochastic Two Points Method for Deep Model Zeroth-order Optimization 提出随机双点法以解决深度模型零阶优化问题 large language model foundation model
19 Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities 提出Audio Flamingo以增强音频理解与对话能力 large language model ✅
20 Decoding Speculative Decoding 提出高效草稿模型以提升大语言模型推理速度 large language model
21 Low-Resource Cross-Domain Singing Voice Synthesis via Reduced Self-Supervised Speech Representations 提出Karaoker-SSL以解决低资源跨域歌声合成问题 TAMP
22 Improving Model Fusion by Training-time Neuron Alignment with Fixed Neuron Anchors 提出训练时神经元对齐方法以提升模型融合效果 foundation model
23 Need a Small Specialized Language Model? Plan Early! 提出小型专用语言模型的高效训练方法 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (12 篇)

#题目一句话要点标签🔗⭐
24 Recent Advances in Predictive Modeling with Electronic Health Records 系统评估电子健康记录中的深度学习预测模型 predictive model
25 Inverse Reinforcement Learning by Estimating Expertise of Demonstrators 提出IRLEED框架以解决异质示范中的逆强化学习问题 reinforcement learning imitation learning inverse reinforcement learning
26 Capturing waste collection planning expert knowledge in a fitness function through preference learning 通过偏好学习构建废物收集规划的适应度函数 preference learning
27 Cooperative Knowledge Distillation: A Learner Agnostic Approach 提出合作知识蒸馏以解决传统蒸馏方法的局限性 distillation
28 To the Max: Reinventing Reward in Reinforcement Learning 提出最大化奖励的强化学习方法以提升学习效率 reinforcement learning ✅
29 Rethinking the Role of Proxy Rewards in Language Model Alignment 提出反向奖励工程以优化语言模型对人类价值的对齐 reinforcement learning large language model ✅
30 Parametric-Task MAP-Elites 提出Parametric-Task MAP-Elites以解决连续多任务优化问题 reinforcement learning deep reinforcement learning PPO
31 Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscape 提出非凸均值场动力学分析以提升Transformer的上下文学习能力 linear attention large language model
32 Efficient Reinforcement Learning for Routing Jobs in Heterogeneous Queueing Systems 提出ACHQ算法以高效路由异构排队系统中的作业 reinforcement learning
33 Near-Optimal Reinforcement Learning with Self-Play under Adaptivity Constraints 提出适应性约束下的近最优强化学习算法以解决多智能体问题 reinforcement learning
34 Bi-CryptoNets: Leveraging Different-Level Privacy for Encrypted Inference 提出Bi-CryptoNets以解决加密推理中的隐私保护问题 distillation OMOMO
35 A Survey on Self-Supervised Learning for Non-Sequential Tabular Data 系统评估自监督学习在非序列表格数据中的应用与挑战 representation learning contrastive learning

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

#题目一句话要点标签🔗⭐
36 Salsa Fresca: Angular Embeddings and Pre-Training for ML Attacks on Learning With Errors 提出三种方法以提升机器学习对LWE问题的攻击效率 OMOMO

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
37 Bass Accompaniment Generation via Latent Diffusion 提出基于潜在扩散的低音伴奏生成系统以解决音乐匹配问题 classifier-free guidance

⬅️ 返回 cs.LG 首页 · 🏠 返回主页