cs.AI（2025-02-05）

📊 共 24 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (18 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 支柱五：交互与反应 (Interaction & Reaction) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (18 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Omni-DNA: A Unified Genomic Foundation Model for Cross-Modal and Multi-Task Learning	Omni-DNA：用于跨模态和多任务学习的统一基因组基础模型	large language model foundation model	✅
2	Reasoning-as-Logic-Units: Scaling Test-Time Reasoning in Large Language Models Through Logic Unit Alignment	提出Reasoning-as-Logic-Units以解决大语言模型推理不一致问题	large language model chain-of-thought
3	SensorChat: Answering Qualitative and Quantitative Questions during Long-Term Multimodal Sensor Interactions	SensorChat：用于长期多模态传感器交互的问答系统，解决定量和定性问题。	large language model multimodal
4	Overcoming Vision Language Model Challenges in Diagram Understanding: A Proof-of-Concept with XML-Driven Large Language Models Solutions	提出一种基于XML驱动的大语言模型方法，解决图表理解中视觉语言模型的挑战	large language model
5	Multimodal Transformer Models for Turn-taking Prediction: Effects on Conversational Dynamics of Human-Agent Interaction during Cooperative Gameplay	提出基于多模态Transformer的轮流发言预测模型，提升人机协作游戏中的对话流畅性。	multimodal
6	A Contemporary Survey of Large Language Model Assisted Program Analysis	综述：大语言模型辅助程序分析的最新进展与未来方向	large language model
7	Large Language Model Guided Self-Debugging Code Generation	PyCapsule：基于大语言模型引导的自调试代码生成框架	large language model
8	A Systematic Approach for Assessing Large Language Models' Test Case Generation Capability	提出GBCV基准，系统评估大语言模型在测试用例生成方面的能力	large language model
9	Metis: A Foundation Speech Generation Model with Masked Generative Pre-training	提出Metis模型以统一解决多种语音生成任务	foundation model multimodal	✅
10	PerPO: Perceptual Preference Optimization via Discriminative Rewarding	PerPO：通过判别式奖励优化多模态大语言模型的感知偏好对齐	large language model multimodal
11	SymAgent: A Neural-Symbolic Self-Learning Agent Framework for Complex Reasoning over Knowledge Graphs	提出SymAgent，通过神经-符号自学习框架增强LLM在知识图谱上的复杂推理能力	large language model
12	Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation	Cache-Craft：通过管理Chunk-Cache提升检索增强生成效率	large language model
13	AdaPhish: AI-Powered Adaptive Defense and Education Resource Against Deceptive Emails	AdaPhish：提出一种基于AI的自适应防御和教育资源，以对抗欺骗性电子邮件。	large language model
14	A Case for Specialisation in Non-Human Entities	论非人实体专业化：强调专用系统在工业中的价值，对抗通用人工智能的盲目发展。	large language model
15	An Empirical Exploration of ChatGPT's Ability to Support Problem Formulation Tasks for Mission Engineering and a Documentation of its Performance Variability	评估ChatGPT在任务工程问题构建中识别利益相关者的能力及性能变异性	large language model
16	Simplifying Formal Proof-Generating Models with ChatGPT and Basic Searching Techniques	利用ChatGPT与搜索技术简化形式化证明生成，并在miniF2F数据集上取得突破	large language model
17	OceanChat: The Effect of Virtual Conversational AI Agents on Sustainable Attitude and Behavior Change	OceanChat：利用虚拟对话AI提升可持续态度和行为	large language model
18	Examining Two Hop Reasoning Through Information Content Scaling	通过信息内容缩放研究Transformer在双跳推理中的能力瓶颈	chain-of-thought

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

#	题目	一句话要点	标签	🔗	⭐
19	YINYANG-ALIGN: Benchmarking Contradictory Objectives and Proposing Multi-Objective Optimization based DPO for Text-to-Image Alignment	YinYangAlign：提出基于多目标优化的DPO方法，提升文本到图像对齐的基准框架	DPO direct preference optimization large language model
20	Learning Generalizable Features for Tibial Plateau Fracture Segmentation Using Masked Autoencoder and Limited Annotations	提出基于掩码自编码器和少量标注的胫骨平台骨折分割方法	masked autoencoder MAE
21	BFS-Prover: Scalable Best-First Tree Search for LLM-based Automatic Theorem Proving	BFS-Prover：一种可扩展的基于最佳优先树搜索的LLM自动定理证明方法	DPO direct preference optimization large language model	✅
22	Lightweight Authenticated Task Offloading in 6G-Cloud Vehicular Twin Networks	提出基于IBC认证的轻量级任务卸载框架，优化6G云车联网中的资源分配。	reinforcement learning deep reinforcement learning DRL
23	Policy Abstraction and Nash Refinement in Tree-Exploiting PSRO	提出基于策略抽象和纳什精炼的树搜索PSRO算法，加速不完美信息博弈的求解。	reinforcement learning deep reinforcement learning DRL

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
24	Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2	AlphaGeometry2：超越奥数金牌选手水平的几何问题求解AI	IMoS	✅

⬅️ 返回 cs.AI 首页 · 🏠 返回主页