cs.LG（2024-12-13）

📊 共 17 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (12) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱一：机器人控制 (Robot Control) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#题目一句话要点标签🔗⭐
1 Higher Order Transformers: Enhancing Stock Movement Prediction On Multimodal Time-Series Data 提出高阶Transformer，增强多模态时间序列数据上的股票走势预测 multimodal
2 Aspen Open Jets: Unlocking LHC Data for Foundation Models in Particle Physics AspenOpenJets：利用LHC开放数据预训练粒子物理领域Foundation模型 foundation model
3 Benchmarking large language models for materials synthesis: the case of atomic layer deposition ALDbench：评估大语言模型在原子层沉积材料合成中的性能 large language model
4 FDM-Bench: A Comprehensive Benchmark for Evaluating Large Language Models in Additive Manufacturing Tasks FDM-Bench：用于评估大语言模型在增材制造任务中性能的综合基准 large language model
5 Activation Sparsity Opportunities for Compressing General Large Language Models 探索激活稀疏性以压缩通用大语言模型，实现边缘设备高效部署。 large language model
6 KVDirect: Distributed Disaggregated LLM Inference KVDirect：实现分布式解耦LLM推理，提升资源利用率与服务能力 large language model
7 METIS: Fast Quality-Aware RAG Systems with Configuration Adaptation METIS：通过配置自适应实现快速高质量的RAG系统 large language model
8 AdvPrefix: An Objective for Nuanced LLM Jailbreaks AdvPrefix：一种用于细粒度大语言模型越狱的目标函数 large language model
9 Detecting LLM Hallucination Through Layer-wise Information Deficiency: Analysis of Ambiguous Prompts and Unanswerable Questions 通过层级信息缺失检测LLM幻觉以应对模糊提示和无解问题 large language model
10 Text2Cypher: Bridging Natural Language and Graph Databases Text2Cypher：构建自然语言到图数据库查询的桥梁，提升非技术用户的使用体验。 large language model
11 Llama 3 Meets MoE: Efficient Upcycling 利用Llama 3高效训练MoE模型：低成本实现性能提升 large language model
12 HashEvict: A Pre-Attention KV Cache Eviction Strategy using Locality-Sensitive Hashing HashEvict：利用局部敏感哈希的预注意力KV缓存淘汰策略，降低LLM推理的GPU内存消耗。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
13 Hybrid Preference Optimization for Alignment: Provably Faster Convergence Rates by Combining Offline Preferences with Online Exploration 提出混合偏好优化(HPO)，结合离线偏好与在线探索，加速RLHF对齐。 reinforcement learning RLHF large language model
14 Solving the Inverse Alignment Problem for Efficient RLHF 提出逆向对齐方法，提升RLHF中奖励模型的训练效率与对齐效果 reinforcement learning RLHF
15 Scaling Combinatorial Optimization Neural Improvement Heuristics with Online Search and Adaptation 提出LRBS搜索策略，提升DRL组合优化启发式算法的性能与泛化性 reinforcement learning deep reinforcement learning DRL

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
16 What constitutes a Deep Fake? The blurry line between legitimate processing and manipulation under the EU AI Act 分析欧盟AI法案对Deepfake的定义，指出其模糊性及潜在问题 manipulation

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

#题目一句话要点标签🔗⭐
17 Data Integration with Fusion Searchlight: Classifying Brain States from Resting-state fMRI 提出Fusion Searchlight框架，融合多指标提升静息态fMRI脑状态分类精度 spatiotemporal

⬅️ 返回 cs.LG 首页 · 🏠 返回主页