cs.AI（2026-07-14）

📊 共 13 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) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1)

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

#题目一句话要点标签🔗⭐
1 FormalAnalyticGeo: A Neural-Symbolic Based Framework for Multimodal Analytic Geometry Problem Generation 提出FormalAnalyticGeo以解决多模态解析几何问题生成 large language model multimodal
2 Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models 提出函数感知中间填充方法以提升编码代理模型能力 foundation model
3 LLMs Can See the Smoke but not the Fire: Evaluating Abductive Reasoning with Elenchos 提出Elenchos框架以评估大语言模型的溯因推理能力 large language model
4 The Sound of Absence: Audio-Language Embedding Models Struggle with Negation 提出NegEval-Audio框架以解决音频语言嵌入模型的否定问题 multimodal
5 Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution 提出E3框架以解决任务复杂性评估问题 large language model
6 Visual Access Boundaries in Vision-Language Model Reasoning 提出视觉访问边界以优化视觉语言模型推理 chain-of-thought
7 Bulkhead: Automated Semantic Detection and Remediation of Container Escape Vulnerabilities 提出Bulkhead框架以自动检测和修复容器逃逸漏洞 large language model
8 Multi-Perspective Agentic Program Repair via Code Property Graphs and Temporal Execution Graphs 提出CT-Repair框架以解决自动程序修复中的上下文问题 large language model
9 Code-MUE: Measuring Code LLMs' Uncertainty through Execution-based Semantic Interaction Graphs 提出Code-MUE以解决代码LLMs不确定性评估问题 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🔗⭐
10 Do We Really Need Multimodal Emotion Language Models Larger Than 1B Parameters? 提出Light-MER以解决大规模多模态情感识别模型的效率问题 distillation large language model multimodal ✅
11 From Observation to Insight: Mechanistic World Models and the Quest for Autonomous Discovery 提出机制世界模型以推动自主科学发现 world model world models representation learning
12 TRACE: An Operational Reasoning Schema for Auditable Agentic Commitments 提出TRACE以解决智能体承诺可审计性问题 reinforcement learning world model world models
13 Knowledge- and Gradient-Guided Reinforcement Learning for Parametrized Action Markov Decision Processes 提出知识与梯度引导的强化学习算法以提升PAMDP样本效率 reinforcement learning

⬅️ 返回 cs.AI 首页 · 🏠 返回主页