cs.AI（2025-04-10）

📊 共 12 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (8 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (8 篇)

#题目一句话要点标签🔗⭐
1 Emergence of psychopathological computations in large language models 大型语言模型涌现精神病理学计算能力的研究 large language model
2 PR-Attack: Coordinated Prompt-RAG Attacks on Retrieval-Augmented Generation in Large Language Models via Bilevel Optimization 提出PR-Attack，通过双层优化协同攻击Prompt和RAG，提升大语言模型对抗攻击的隐蔽性和有效性。 large language model
3 Enhancing Large Language Models through Neuro-Symbolic Integration and Ontological Reasoning 提出神经符号集成方法，结合本体推理提升大语言模型的事实准确性。 large language model
4 Orchestrating Agents and Data for Enterprise: A Blueprint Architecture for Compound AI 面向企业级应用的复合AI蓝图架构：通过编排Agent与数据提升LLM应用能力 large language model
5 Beating Transformers using Synthetic Cognition 提出基于合成认知的序列处理机制，在DNA序列分类任务中超越Transformer模型。 foundation model
6 We Are All Creators: Generative AI, Collective Knowledge, and the Path Towards Human-AI Synergy 探讨生成式AI与人类协同，促进创新、民主化表达及解决复杂挑战 foundation model
7 APSQ: Additive Partial Sum Quantization with Algorithm-Hardware Co-Design 提出APSQ：一种算法-硬件协同设计的加性部分和量化方法，降低DNN加速器功耗 large language model ✅
8 Evaluating LLMs for Visualization Tasks 评估大型语言模型在可视化任务中的能力与局限性 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🔗⭐
9 2D-Curri-DPO: Two-Dimensional Curriculum Learning for Direct Preference Optimization 提出2D-Curri-DPO，通过二维课程学习优化语言模型对人类偏好的对齐。 reinforcement learning DPO direct preference optimization
10 Enhancing Player Enjoyment with a Two-Tier DRL and LLM-Based Agent System for Fighting Games 提出基于双层DRL和LLM的格斗游戏Agent系统，提升玩家游戏乐趣 reinforcement learning deep reinforcement learning DRL
11 Genetic Programming with Reinforcement Learning Trained Transformer for Real-World Dynamic Scheduling Problems 提出基于强化学习训练Transformer的遗传编程(GPRT)方法，解决现实动态调度问题。 reinforcement learning

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
12 S2Vec: Self-Supervised Geospatial Embeddings for the Built Environment S2Vec：面向建成环境的自监督地理空间嵌入学习框架 spatial relationship multimodal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页