cs.AI（2025-09-07）

📊 共 14 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (9 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#题目一句话要点标签🔗⭐
1 Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs 评估大型语言模型在多模态提示注入攻击下的脆弱性并探讨防御方法 large language model multimodal
2 Language-Native Materials Processing Design by Lightly Structured Text Database and Reasoning Large Language Model 提出基于轻结构化文本数据库和推理大语言模型的材料设计方法 large language model
3 Empirical Study of Code Large Language Models for Binary Security Patch Detection 利用代码大语言模型进行二进制安全补丁检测的实证研究 large language model
4 Automated Unity Game Template Generation from GDDs via NLP and Multi-Modal LLMs 提出一种基于NLP和多模态LLM的自动化Unity游戏模板生成框架，提升游戏开发效率。 large language model
5 From Eigenmodes to Proofs: Integrating Graph Spectral Operators with Symbolic Interpretable Reasoning 提出Spectral NSR，通过图谱算子融合符号推理，提升知识图谱推理能力。 large language model
6 Beamforming-LLM: What, Where and When Did I Miss? 提出Beamforming-LLM，通过波束成形和LLM实现多发言者场景下的对话语义回忆。 large language model
7 From Long to Short: LLMs Excel at Trimming Own Reasoning Chains 提出EDIT方法，提升大语言模型在复杂推理任务中的效率和可解释性 instruction following
8 DecoupleSearch: Decouple Planning and Search via Hierarchical Reward Modeling DecoupleSearch：通过分层奖励建模解耦规划与搜索，提升Agentic RAG性能 large language model
9 MapAgent: A Hierarchical Agent for Geospatial Reasoning with Dynamic Map Tool Integration 提出MapAgent，用于动态地图工具集成和地理空间推理的分层Agent框架 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
10 Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL 提出基于强化学习的动态推理效率奖励DRER，提升大语言模型的推理质量。 reinforcement learning large language model chain-of-thought ✅
11 Proof2Silicon: Prompt Repair for Verified Code and Hardware Generation via Reinforcement Learning Proof2Silicon：基于强化学习的提示修复，实现可验证代码与硬件生成 reinforcement learning large language model
12 Distillation of CNN Ensemble Results for Enhanced Long-Term Prediction of the ENSO Phenomenon 通过CNN集成结果蒸馏，提升ENSO现象的长期预测能力 distillation
13 Reverse-Engineered Reasoning for Open-Ended Generation 提出逆向工程推理(REER)方法，用于开放式生成任务，性能媲美GPT-4o。 reinforcement learning distillation

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

#题目一句话要点标签🔗⭐
14 GeoAnalystBench: A GeoAI benchmark for assessing large language models for spatial analysis workflow and code generation GeoAnalystBench：评估大语言模型在空间分析工作流和代码生成方面的GeoAI基准 spatial relationship large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页