cs.AI（2025-03-21）

📊 共 16 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) (10 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (5) 支柱六：视频提取与匹配 (Video Extraction) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗⭐
1 Assessing Consistency and Reproducibility in the Outputs of Large Language Models: Evidence Across Diverse Finance and Accounting Tasks 评估大语言模型在金融和会计任务中的一致性和可重复性 large language model
2 Large Language Models (LLMs) for Source Code Analysis: applications, models and datasets 综述：大型语言模型在源代码分析中的应用、模型与数据集 large language model
3 Does Chain-of-Thought Reasoning Help Mobile GUI Agent? An Empirical Study 研究链式思考推理对移动GUI智能体的性能影响，发现其收益与代价并存 chain-of-thought ✅
4 Your voice is your voice: Supporting Self-expression through Speech Generation and LLMs in Augmented and Alternative Communication 提出Speak Ease以解决AAC用户自我表达不足问题 large language model multimodal
5 HCAST: Human-Calibrated Autonomy Software Tasks HCAST：提出人类校准的自主软件任务基准，评估AI在软件工程等领域的自主能力。 foundation model
6 CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities CVE-Bench：评估AI Agent利用真实Web应用漏洞能力的基准测试 large language model
7 A Study of LLMs' Preferences for Libraries and Programming Languages 研究揭示LLM在代码生成中对特定库和语言的偏好及潜在风险 large language model
8 RustEvo^2: An Evolving Benchmark for API Evolution in LLM-based Rust Code Generation RustEvo：一个演进的基准测试，用于评估LLM在Rust代码生成中API演变的处理能力 large language model ✅
9 Understanding Social Support Needs in Questions: A Hybrid Approach Integrating Semi-Supervised Learning and LLM-based Data Augmentation 提出HA-SOS框架，结合半监督学习和LLM数据增强，解决在线问答社区中的社会支持需求识别问题 large language model
10 MAPS: Multi-Agent Personality Shaping for Collaborative Reasoning 提出MAPS框架，通过多Agent人格塑造和内部批判提升协同推理能力 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
11 Real-Time Diffusion Policies for Games: Enhancing Consistency Policies with Q-Ensembles CPQE：结合Q-Ensembles的一致性策略，实现游戏AI实时扩散策略 policy learning diffusion policy consistency policy
12 A New Segment Routing method with Swap Node Selection Strategy Based on Deep Reinforcement Learning for Software Defined Network 提出基于深度强化学习的SDN分段路由方法，优化流表下发时间并提升网络性能。 reinforcement learning deep reinforcement learning DRL
13 Autonomous Radiotherapy Treatment Planning Using DOLA: A Privacy-Preserving, LLM-Based Optimization Agent DOLA：一种保护隐私的、基于LLM的自主放疗治疗计划优化Agent reinforcement learning large language model chain-of-thought
14 Capturing Individual Human Preferences with Reward Features 提出基于奖励特征的个性化奖励模型，用于捕获个体人类偏好 reinforcement learning large language model
15 Neural-Guided Equation Discovery 提出神经引导的方程发现系统MGMT，探索不同架构在表格数据方程发现中的应用。 reinforcement learning contrastive learning

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
16 The CASTLE 2024 Dataset: Advancing the Art of Multimodal Understanding CASTLE 2024：一个用于推进多模态理解的全新第一人称和第三人称视角视频数据集 egocentric multimodal ✅

⬅️ 返回 cs.AI 首页 · 🏠 返回主页