cs.AI（2026-04-22）

📊 共 17 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) (12 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#题目一句话要点标签🔗⭐
1 Text Steganography with Dynamic Codebook and Multimodal Large Language Model 提出基于动态码本和多模态大语言模型的文本隐写术，提升安全性和实用性 large language model multimodal
2 AROMA: Augmented Reasoning Over a Multimodal Architecture for Virtual Cell Genetic Perturbation Modeling AROMA：用于虚拟细胞遗传扰动建模的增强推理多模态架构 multimodal ✅
3 Large Language Models Outperform Humans in Fraud Detection and Resistance to Motivated Investor Pressure 大语言模型在欺诈检测中优于人类，且更能抵抗投资者压力 large language model
4 Where and What: Reasoning Dynamic and Implicit Preferences in Situated Conversational Recommendation 提出SiPeR框架，解决情境对话推荐中动态隐式偏好推理难题 large language model multimodal ✅
5 ATIR: Towards Audio-Text Interleaved Contextual Retrieval 提出ATIR任务与基准，解决音频-文本交错上下文检索难题 large language model multimodal
6 Automatic Ontology Construction Using LLMs as an External Layer of Memory, Verification, and Planning for Hybrid Intelligent Systems 提出一种混合智能系统架构，利用LLM和外部本体知识库实现可验证的推理和规划。 large language model
7 Early-Stage Product Line Validation Using LLMs: A Study on Semi-Formal Blueprint Analysis 利用LLM进行早期产品线验证：半形式化蓝图分析研究 large language model
8 Self-Awareness before Action: Mitigating Logical Inertia via Proactive Cognitive Awareness 提出SABA框架，通过主动认知推理弥补大语言模型在非交互式谜题中逻辑惯性问题。 large language model
9 LLM-guided phase diagram construction through high-throughput experimentation 利用LLM指导高通量实验，加速多元合金相图构建 large language model
10 Memory-Augmented LLM-based Multi-Agent System for Automated Feature Generation on Tabular Data 提出MALMAS，一种基于记忆增强LLM的多智能体系统，用于表格数据自动特征生成。 large language model ✅
11 Taint-Style Vulnerability Detection and Confirmation for Node.js Packages Using LLM Agent Reasoning 提出LLMVD.js，利用LLM Agent推理检测Node.js包中的污点漏洞 large language model
12 EvoAgent: An Evolvable Agent Framework with Skill Learning and Multi-Agent Delegation EvoAgent：一种可进化Agent框架，通过技能学习和多Agent委托解决复杂任务。 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🔗⭐
13 V-tableR1: Process-Supervised Multimodal Table Reasoning with Critic-Guided Policy Optimization V-tableR1：提出流程监督的多模态表格推理框架，通过评论家引导的策略优化实现可验证的推理。 reinforcement learning large language model multimodal
14 Self-Guided Plan Extraction for Instruction-Following Tasks with Goal-Conditional Reinforcement Learning SuperIgor：基于自学习计划提取的指令跟随任务框架 reinforcement learning instruction following
15 HiPO: Hierarchical Preference Optimization for Adaptive Reasoning in LLMs HiPO：分层偏好优化提升LLM在复杂推理任务中的自适应推理能力 preference learning DPO direct preference optimization
16 Vibrotactile Preference Learning: Uncertainty-Aware Preference Learning for Personalized Vibration Feedback 提出VPL：基于高斯过程不确定性感知偏好学习的个性化振动反馈系统 preference learning

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

#题目一句话要点标签🔗⭐
17 AI models of unstable flow exhibit hallucination 提出DeepFingers框架，解决AI流体模型中不稳定性流动模拟的幻觉问题 spatiotemporal large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页