cs.LG（2024-07-10）

📊 共 17 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) (8 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (7 🔗2) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱八：物理动画 (Physics-based Animation) (1)

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

#题目一句话要点标签🔗⭐
1 Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning 提出两种悲观离线强化学习算法，解决线性MDP中风险敏感策略优化问题 reinforcement learning offline RL offline reinforcement learning
2 Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization 提出Dr. DPO，通过分布鲁棒优化提升语言模型在噪声数据下的对齐效果 DPO direct preference optimization large language model ✅
3 Real-time system optimal traffic routing under uncertainties -- Can physics models boost reinforcement learning? TransRL：融合物理模型与强化学习，实现不确定性下的实时系统最优交通路径规划 reinforcement learning PPO SAC
4 Advancements in Recommender Systems: A Comprehensive Analysis Based on Data, Algorithms, and Evaluation 综述性分析推荐系统在数据、算法和评估方面的挑战与未来发展方向 reinforcement learning deep reinforcement learning multimodal
5 Disentangled Representation Learning with the Gromov-Monge Gap 提出基于Gromov-Monge Gap的解耦表示学习方法，提升几何特征保持能力。 representation learning
6 Reinforcement Learning of Adaptive Acquisition Policies for Inverse Problems 提出基于强化学习的自适应采集策略，用于求解逆问题。 reinforcement learning
7 Deep-Graph-Sprints: Accelerated Representation Learning in Continuous-Time Dynamic Graphs Deep-Graph-Sprints：加速连续时间动态图中的表征学习 representation learning
8 Resource Allocation for Twin Maintenance and Computing Task Processing in Digital Twin Vehicular Edge Computing Network 提出基于多智能体深度强化学习的资源协同调度算法，解决数字孪生车联网边缘计算中的资源分配问题。 reinforcement learning deep reinforcement learning

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

#题目一句话要点标签🔗⭐
9 EfficientQAT: Efficient Quantization-Aware Training for Large Language Models 提出EfficientQAT，一种高效的大语言模型量化感知训练方法，显著降低训练资源需求。 large language model multimodal ✅
10 GLBench: A Comprehensive Benchmark for Graph with Large Language Models GLBench：用于图与大语言模型结合的综合性评测基准 large language model zero-shot transfer ✅
11 A Critical Review of Causal Reasoning Benchmarks for Large Language Models 对大型语言模型因果推理基准的批判性综述 large language model
12 Fine-Tuning Large Language Models with User-Level Differential Privacy 提出用户级差分隐私LLM微调算法，保障用户数据安全。 large language model
13 Toto: Time Series Optimized Transformer for Observability Datadog发布Toto：面向可观测性的时序优化Transformer基础模型 foundation model
14 OpenDiLoCo: An Open-Source Framework for Globally Distributed Low-Communication Training OpenDiLoCo：用于大规模语言模型训练的开源分布式低通信框架 large language model
15 Transformer Block Coupling and its Correlation with Generalization in LLMs 揭示LLM Transformer块耦合现象，及其与泛化能力的正相关性 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🔗⭐
16 Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferences 提出PaLoRA：一种参数高效的Pareto前沿学习方法，用于解决多任务学习中的权衡问题。 scene understanding

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

#题目一句话要点标签🔗⭐
17 Pentagonal Photonic Crystal Mirrors: Scalable Lightsails with Enhanced Acceleration via Neural Topology Optimization 利用神经拓扑优化设计五边形光子晶体反射镜，实现可扩展光帆并提升加速性能 PHC

⬅️ 返回 cs.LG 首页 · 🏠 返回主页