cs.AI（2025-12-22）

📊 共 8 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) (7 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (7 篇)

#题目一句话要点标签🔗⭐
1 Can Large Language Models Improve Venture Capital Exit Timing After IPO? 利用大语言模型改进风险投资在IPO后的退出时机选择 large language model
2 Clustering-based Transfer Learning for Dynamic Multimodal MultiObjective Evolutionary Algorithm 提出基于聚类迁移学习的动态多模态多目标进化算法，解决动态环境下的多模态优化问题。 multimodal
3 GamiBench: Evaluating Spatial Reasoning and 2D-to-3D Planning Capabilities of MLLMs with Origami Folding Tasks GamiBench：通过折纸任务评估多模态大语言模型空间推理和2D到3D规划能力 large language model multimodal instruction following ✅
4 The Erasure Illusion: Stress-Testing the Generalization of LLM Forgetting Evaluation 提出近端代理生成（PSG）框架，用于压力测试LLM遗忘评估的泛化能力，揭示现有评估方法的局限性。 large language model
5 PromptScreen: Efficient Jailbreak Mitigation Using Semantic Linear Classification in a Multi-Staged Pipeline PromptScreen：一种多阶段流水线中基于语义线性分类的高效越狱攻击缓解方法 large language model
6 Reflection-Driven Control for Trustworthy Code Agents 提出反射驱动控制，提升代码Agent安全性和可信度 large language model
7 Psychometric Comparability of LLM-Based Digital Twins 评估LLM数字孪生体的心理测量可比性，揭示其在模拟人类认知和行为方面的局限性与优势。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
8 Training Multimodal Large Reasoning Models Needs Better Thoughts: A Three-Stage Framework for Long Chain-of-Thought Synthesis and Selection 提出SynSelect框架，为多模态大模型生成高质量长链推理训练数据。 reinforcement learning multimodal chain-of-thought

⬅️ 返回 cs.AI 首页 · 🏠 返回主页