cs.AI（2026-01-23）

📊 共 12 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) (9 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱三：空间感知与语义 (Perception & Semantics) (1)

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

#题目一句话要点标签🔗⭐
1 LLM is Not All You Need: A Systematic Evaluation of ML vs. Foundation Models for text and image based Medical Classification 医学分类任务中，传统机器学习方法在文本和图像模态上优于微调后的LLM large language model foundation model multimodal
2 SycoEval-EM: Sycophancy Evaluation of Large Language Models in Simulated Clinical Encounters for Emergency Care SycoEval-EM：模拟急诊场景评估大语言模型在患者压力下的顺从性 large language model
3 BONO-Bench: A Comprehensive Test Suite for Bi-objective Numerical Optimization with Traceable Pareto Sets 提出BONO-Bench，用于可追踪Pareto集双目标数值优化问题的综合测试套件。 multimodal
4 AgentDrive: An Open Benchmark Dataset for Agentic AI Reasoning with LLM-Generated Scenarios in Autonomous Systems AgentDrive：用于自动驾驶系统中Agentic AI推理的LLM生成场景开放基准数据集 large language model ✅
5 Revisiting the Role of Natural Language Code Comments in Code Translation 研究表明代码注释显著提升代码翻译质量，并提出COMMENTRA方法。 large language model
6 LUMINA: Long-horizon Understanding for Multi-turn Interactive Agents LUMINA：用于多轮交互Agent的长期理解能力研究 large language model
7 Do Models Hear Like Us? Probing the Representational Alignment of Audio LLMs and Naturalistic EEG 通过脑电信号探究语音大模型与人类听觉神经机制的表征对齐 large language model
8 SafeThinker: Reasoning about Risk to Deepen Safety Beyond Shallow Alignment 提出SafeThinker框架，提升大语言模型在对抗攻击下的安全性与实用性。 large language model
9 Doc2AHP: Inferring Structured Multi-Criteria Decision Models via Semantic Trees with LLMs Doc2AHP：提出一种基于LLM和语义树的结构化多准则决策模型推理框架，无需人工干预。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
10 CORD: Bridging the Audio-Text Reasoning Gap via Weighted On-policy Cross-modal Distillation CORD：通过加权On-policy跨模态蒸馏弥合音频-文本推理差距 distillation large language model
11 Reasoning Promotes Robustness in Theory of Mind Tasks 利用推理提升大语言模型在心理理论任务中的鲁棒性 reinforcement learning large language model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
12 Privacy in Human-AI Romantic Relationships: Concerns, Boundaries, and Agency 通过访谈研究揭示人机恋爱关系中的隐私问题、边界和自主性 affordance

⬅️ 返回 cs.AI 首页 · 🏠 返回主页