cs.AI（2026-02-10）

📊 共 17 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) (10) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 支柱一：机器人控制 (Robot Control) (1) 支柱八：物理动画 (Physics-based Animation) (1)

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

#题目一句话要点标签🔗⭐
1 Would a Large Language Model Pay Extra for a View? Inferring Willingness to Pay from Subjective Choices 利用大语言模型进行主观选择偏好推断，评估其支付意愿 large language model
2 Computing Conditional Shapley Values Using Tabular Foundation Models 利用表格型预训练模型加速条件Shapley值的计算 foundation model
3 A Behavioral Fingerprint for Large Language Models: Provenance Tracking via Refusal Vectors 提出基于拒绝向量的行为指纹方法，用于追踪大型语言模型的知识产权。 large language model
4 LLMAC: A Global and Explainable Access Control Framework with Large Language Model 提出LLMAC，利用大语言模型实现全局可解释的访问控制框架 large language model
5 GHS-TDA: A Synergistic Reasoning Framework Integrating Global Hypothesis Space with Topological Data Analysis 提出GHS-TDA框架，融合全局假设空间与拓扑数据分析，提升LLM推理能力 large language model chain-of-thought
6 Kunlun: Establishing Scaling Laws for Massive-Scale Recommendation Systems through Unified Architecture Design Kunlun：通过统一架构设计，为大规模推荐系统建立可预测的扩展法则。 large language model
7 SWE-AGI: Benchmarking Specification-Driven Software Construction with MoonBit in the Era of Autonomous Agents SWE-AGI：利用MoonBit评估自主Agent在规范驱动下构建软件的能力 large language model
8 Beyond Input-Output: Rethinking Creativity through Design-by-Analogy in Human-AI Collaboration 扩展类比设计（DbA）在人机协作中的应用，提升创造力并缓解设计固化 foundation model
9 Accelerating Post-Quantum Cryptography via LLM-Driven Hardware-Software Co-Design 利用LLM驱动的软硬件协同设计加速后量子密码学 large language model
10 Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judge 提出AgentAuditor，通过推理树审核多智能体LLM，提升复杂推理任务准确率。 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 Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning 提出Agent World Model，用于大规模智能体强化学习的无限合成环境 reinforcement learning world model large language model ✅
12 Bridging Efficiency and Transparency: Explainable CoT Compression in Multimodal Large Reasoning Models 提出XMCC，通过可解释的强化学习压缩多模态大模型中的CoT，提升推理效率。 reinforcement learning multimodal
13 Autoregressive Direct Preference Optimization 提出自回归直接偏好优化(ADPO)，提升大语言模型对齐人类偏好的效率。 DPO direct preference optimization large language model
14 Efficient Unsupervised Environment Design through Hierarchical Policy Representation Learning 提出基于分层策略表示学习的高效无监督环境设计方法 representation learning teacher-student
15 CODE-SHARP: Continuous Open-ended Discovery and Evolution of Skills as Hierarchical Reward Programs CODE-SHARP：利用分层奖励程序持续开放地发现和进化技能 reinforcement learning foundation model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
16 P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads 提出P1-VL视觉语言模型，解决物理奥赛中视觉感知与科学推理的桥梁问题 manipulation reinforcement learning large language model

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
17 Detecting radar targets swarms in range profiles with a partially complex-valued neural network 提出一种部分复值神经网络，用于检测雷达距离像中的密集目标群。 PULSE

⬅️ 返回 cs.AI 首页 · 🏠 返回主页