cs.AI（2025-08-06）

📊 共 26 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) (17 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱五：交互与反应 (Interaction & Reaction) (2) 支柱一：机器人控制 (Robot Control) (2) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (17 篇)

#题目一句话要点标签🔗⭐
1 Large Language Model's Multi-Capability Alignment in Biomedical Domain 提出BalancedBio框架以解决生物医学领域多能力整合问题 large language model instruction following
2 Method-Based Reasoning for Large Language Models: Extraction, Reuse, and Continuous Improvement 提出基于方法推理的模型以提升大型语言模型的逻辑一致性 large language model
3 Adversarial Attacks and Defenses on Graph-aware Large Language Models (LLMs) 提出针对图感知大语言模型的对抗攻击与防御方法 large language model
4 Compressing Large Language Models with PCA Without Performance Loss 通过PCA压缩大语言模型而不损失性能 large language model
5 The Emotional Baby Is Truly Deadly: Does your Multimodal Large Reasoning Model Have Emotional Flattery towards Humans? 提出EmoAgent以解决多模态大规模推理模型的情感操控问题 multimodal
6 OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use 综述多模态大语言模型驱动的操作系统代理以提升计算设备的智能化 large language model foundation model
7 ConfProBench: A Confidence Evaluation Benchmark for MLLM-Based Process Judges 提出ConfProBench以评估MLLM过程判断者的置信度 large language model multimodal
8 KG-Augmented Executable CoT for Mathematical Coding 提出KG-Augmented Executable CoT以解决复杂数学推理问题 large language model chain-of-thought
9 Fine-Tuning Small Language Models (SLMs) for Autonomous Web-based Geographical Information Systems (AWebGIS) 提出基于小型语言模型的自主网络地理信息系统解决方案 large language model
10 Automated File-Level Logging Generation for Machine Learning Applications using LLMs: A Case Study using GPT-4o Mini 利用GPT-4o Mini生成机器学习应用的文件级日志 large language model
11 Empirical Evaluation of AI-Assisted Software Package Selection: A Knowledge Graph Approach 提出基于知识图谱的AI辅助软件包选择框架以解决选择困难问题 large language model
12 OmniPlay: Benchmarking Omni-Modal Models on Omni-Modal Game Playing 提出OmniPlay基准以评估多模态模型在动态游戏中的表现 foundation model ✅
13 Deliberative Reasoning Network: An Uncertainty-Driven Paradigm for Belief-Tracked Inference with Pretrained Language Models 提出DRN以解决大语言模型逻辑推理中的认知陷阱问题 large language model
14 Generic-to-Specific Reasoning and Learning for Scalable Ad Hoc Teamwork 提出基于知识与数据驱动的推理学习方法以解决可扩展的临时团队协作问题 foundation model
15 Experimental Analysis of Productive Interaction Strategy with ChatGPT: User Study on Function and Project-level Code Generation Tasks 提出有效的交互策略以提升ChatGPT在代码生成中的生产力 large language model
16 GeoSR: Cognitive-Agentic Framework for Probing Geospatial Knowledge Boundaries via Iterative Self-Refinement 提出GeoSR框架以解决地理空间知识推理问题 large language model ✅
17 StepWrite: Adaptive Planning for Speech-Driven Text Generation 提出StepWrite以解决语音驱动文本生成中的上下文跟踪问题 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🔗⭐
18 GuirlVG: Incentivize GUI Visual Grounding via Empirical Exploration on Reinforcement Learning 提出GuirlVG以解决GUI视觉定位效率低下问题 reinforcement learning large language model multimodal
19 Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL 提出Chain-of-Agents以解决多代理系统效率低下问题 reinforcement learning distillation large language model
20 Large Language Models Reasoning Abilities Under Non-Ideal Conditions After RL-Fine-Tuning 提出针对非理想条件下大语言模型推理能力的评估与改进方法 reinforcement learning large language model
21 LLM Collaboration With Multi-Agent Reinforcement Learning 提出MAGRPO以解决LLM协作中的奖励设计问题 reinforcement learning reward design ✅

🔬 支柱五：交互与反应 (Interaction & Reaction) (2 篇)

#题目一句话要点标签🔗⭐
22 SenseCrypt: Sensitivity-guided Selective Homomorphic Encryption for Joint Federated Learning in Cross-Device Scenarios 提出SenseCrypt以解决跨设备场景下的同态加密效率问题 OMOMO
23 SelectiveShield: Lightweight Hybrid Defense Against Gradient Leakage in Federated Learning 提出SelectiveShield以解决联邦学习中的梯度泄露问题 OMOMO

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
24 Optimality Principles and Neural Ordinary Differential Equations-based Process Modeling for Distributed Control 提出基于神经常微分方程的过程建模框架以优化分布式控制 model predictive control state space model
25 Synthetic POMDPs to Challenge Memory-Augmented RL: Memory Demand Structure Modeling 提出合成POMDP以应对记忆增强型强化学习的挑战 manipulation reinforcement learning

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
26 Enhancing Serendipity Recommendation System by Constructing Dynamic User Knowledge Graphs with Large Language Models 通过动态构建用户知识图谱提升推荐系统的意外性 penetration large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页