cs.AI（2024-08-19）

📊 共 23 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (13 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (8 🔗1) 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) (13 篇)

#题目一句话要点标签🔗⭐
1 Harnessing Multimodal Large Language Models for Multimodal Sequential Recommendation 提出MLLM-MSR模型，利用多模态大语言模型增强多模态序列推荐效果。 large language model multimodal
2 Development of an AI Anti-Bullying System Using Large Language Model Key Topic Detection 提出基于大语言模型的AI反欺凌系统，用于识别和应对社交媒体欺凌攻击 large language model
3 DELIA: Diversity-Enhanced Learning for Instruction Adaptation in Large Language Models DELIA：通过多样性增强学习提升大语言模型指令适应能力 large language model
4 MSDiagnosis: A Benchmark for Evaluating Large Language Models in Multi-Step Clinical Diagnosis MSDiagnosis：提出一个多步骤临床诊断基准，并设计结合前向、后向推理与自省的诊断框架。 large language model
5 Simulating Field Experiments with Large Language Models 提出两种提示策略，利用大语言模型模拟社会科学领域实验，扩展LLM应用场景。 large language model
6 A Comparison of Large Language Model and Human Performance on Random Number Generation Tasks 对比大型语言模型与人类在随机数生成任务中的表现，揭示LLM的认知偏差 large language model
7 Are LLMs Any Good for High-Level Synthesis? 探索LLM在高级综合中的应用，评估其在硬件设计中的潜力 large language model
8 LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domain LegalBench-RAG：法律领域检索增强生成评测基准，关注精准检索片段 large language model ✅
9 A Disguised Wolf Is More Harmful Than a Toothless Tiger: Adaptive Malicious Code Injection Backdoor Attack Leveraging User Behavior as Triggers 提出基于用户行为触发的自适应恶意代码注入后门攻击，提升代码生成模型的安全性 large language model
10 Demystifying the Communication Characteristics for Distributed Transformer Models 剖析分布式Transformer模型通信特性，优化大规模模型训练效率 large language model
11 Customizing Language Models with Instance-wise LoRA for Sequential Recommendation 提出iLoRA，通过实例LoRA定制化语言模型，提升序列推荐性能。 large language model ✅
12 Fine-Grained and Thematic Evaluation of LLMs in Social Deduction Game 提出细粒度和主题分析方法，评估LLM在社交推理游戏中的表现 large language model
13 GoNoGo: An Efficient LLM-based Multi-Agent System for Streamlining Automotive Software Release Decision-Making GoNoGo：高效的基于LLM的多智能体系统，用于简化汽车软件发布决策 large language model

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

#题目一句话要点标签🔗⭐
14 Reset-free Reinforcement Learning with World Models 提出MoReFree，一种基于世界模型的免重置强化学习方法，提升数据效率。 reinforcement learning policy learning world model ✅
15 Enhancing Reinforcement Learning Through Guided Search 提出基于蒙特卡洛树搜索引导的强化学习方法，提升离策略学习在Atari游戏中的性能。 reinforcement learning policy learning offline RL
16 Minor DPO reject penalty to increase training robustness 提出MinorDPO，通过引入reject惩罚增强DPO训练的鲁棒性 reinforcement learning RLHF DPO
17 Demystifying Reinforcement Learning in Production Scheduling via Explainable AI 提出基于假设检验的工作流，提升DRL生产调度决策的可解释性 reinforcement learning deep reinforcement learning DRL
18 Debiased Contrastive Representation Learning for Mitigating Dual Biases in Recommender Systems 提出DCLMDB框架，通过解偏对比学习缓解推荐系统中流行度和一致性双重偏差 representation learning contrastive learning
19 Efficient Reinforcement Learning in Probabilistic Reward Machines 提出高效算法解决带概率奖励机器的强化学习问题 reinforcement learning
20 BrewCLIP: A Bifurcated Representation Learning Framework for Audio-Visual Retrieval BrewCLIP：用于音频-视觉检索的双分支表征学习框架 representation learning
21 Contextual Dual Learning Algorithm with Listwise Distillation for Unbiased Learning to Rank 提出CDLA-LD算法，通过上下文双重学习和列表式知识蒸馏解决排序学习中的位置偏差和上下文偏差问题 distillation

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
22 ARMADA: Attribute-Based Multimodal Data Augmentation 提出ARMADA：一种基于属性的知识引导多模态数据增强方法，提升模型性能。 manipulation large language model multimodal

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

#题目一句话要点标签🔗⭐
23 Principle Driven Parameterized Fiber Model based on GPT-PINN Neural Network 提出基于GPT-PINN的参数化光纤模型，提升光纤通信优化效率。 PULSE

⬅️ 返回 cs.AI 首页 · 🏠 返回主页