cs.LG（2024-09-26）

📊 共 17 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (8 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (7 🔗4) 支柱一：机器人控制 (Robot Control) (2 🔗1)

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

#题目一句话要点标签🔗⭐
1 Inverse Reinforcement Learning with Multiple Planning Horizons 提出多规划视野下的逆强化学习算法，解决专家折扣因子未知时的奖励函数学习问题 reinforcement learning inverse reinforcement learning
2 Spatiotemporal Graph Learning with Direct Volumetric Information Passing and Feature Enhancement CeFeGNN：结合体数据信息传递与特征增强的时空图学习框架 representation learning spatiotemporal
3 Diversity-Driven Synthesis: Enhancing Dataset Distillation through Directed Weight Adjustment 提出基于动态权重调整的合成数据集多样性增强方法，提升数据集蒸馏性能。 distillation ✅
4 Criticality and Safety Margins for Reinforcement Learning 提出强化学习安全性评估框架，通过安全边际量化策略风险 reinforcement learning
5 A Survey on Neural Architecture Search Based on Reinforcement Learning 综述性研究：基于强化学习的神经架构搜索方法 reinforcement learning
6 Efficient Bias Mitigation Without Privileged Information 提出TAB框架，无需特权信息高效缓解深度学习模型中的偏见问题 privileged information
7 FlowMAC: Conditional Flow Matching for Audio Coding at Low Bit Rates FlowMAC：基于条件流匹配的低码率高质量音频编码 flow matching
8 Dataset Distillation-based Hybrid Federated Learning on Non-IID Data 提出基于数据集蒸馏的混合联邦学习框架HFLDD，解决非独立同分布数据下的通信开销问题。 distillation

🔬 支柱九：具身大模型 (Embodied Foundation Models) (7 篇)

#题目一句话要点标签🔗⭐
9 Multimodal Banking Dataset: Understanding Client Needs through Event Sequences 发布多模态银行数据集MBD，用于通过事件序列理解客户需求，并提出多模态融合基线。 large language model multimodal ✅
10 Graph Reasoning with Large Language Models via Pseudo-code Prompting 提出伪代码提示方法，提升大语言模型在图推理任务上的性能 large language model
11 Efficient Arbitrary Precision Acceleration for Large Language Models on GPU Tensor Cores 提出一种高效的任意精度加速方案，用于在GPU Tensor Core上加速大语言模型。 large language model
12 RmGPT: A Foundation Model with Generative Pre-trained Transformer for Fault Diagnosis and Prognosis in Rotating Machinery RmGPT：用于旋转机械故障诊断与预测的生成式预训练Transformer基础模型 foundation model ✅
13 An Adversarial Perspective on Machine Unlearning for AI Safety 从对抗视角评估AI模型卸载学习的安全性，揭示现有方法的脆弱性 large language model
14 Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models 提出LM-GC，利用大语言模型作为零样本梯度压缩器，提升分布式学习效率。 large language model ✅
15 HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection HaloScope：利用未标注LLM生成数据进行幻觉检测 large language model ✅

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
16 DMC-VB: A Benchmark for Representation Learning for Control with Visual Distractors 提出DMC-VB基准测试，用于评估视觉干扰下控制任务的表征学习鲁棒性 locomotion reinforcement learning policy learning ✅
17 Least Squares and Marginal Log-Likelihood Model Predictive Control using Normalizing Flows 提出基于Normalizing Flows的最小二乘与边际对数似然MPC，用于解决随机动态过程控制问题。 MPC model predictive control

⬅️ 返回 cs.LG 首页 · 🏠 返回主页