AI 大模型

大模型推理能力

大模型数学、逻辑、规划、多步推理和测试时计算能力。

2025-11-13 至 2025-11-13 共收录 6 篇信号源：cs.CL, cs.AI, cs.LG

1. 视觉空间推理 6 篇

2511.08942 2025-11-13 cs.RO cs.AI 85%

Think, Remember, Navigate: Zero-Shot Object-Goal Navigation with VLM-Powered Reasoning

Mobin Habibpour, Fatemeh Afghah

机构 * Holcombe Department of Electrical and Computer Engineering（霍尔科姆电气与计算机工程系）； Clemson University（克莱姆森大学）

专题命中视觉空间推理：reasoning(title,abstract)；chain-of-thought(abstract)；planning(abstract)；分类 cs.AI

2511.08609 2025-11-13 cs.CV cs.AI cs.LG 62%

Case Study: Transformer-Based Solution for the Automatic Digitization of Gas Plants

I. Bailo, F. Buonora, G. Ciarfaglia, L. T. Consoli, A. Evangelista, M. Gabusi, M. Ghiani, C. Petracca Ciavarella, F. Picariello, F. Sarcina, F. Tuosto, V. Zullo, L. Airoldi, G. Bruno, D. D. Gobbo, S. Pezzenati, G. A. Tona

机构 * Engineering Group（工程集团）； Snam S.p.A.（Snam公司）

专题命中视觉空间推理：reasoning(abstract)；分类 cs.AI、cs.LG

2511.08892 2025-11-13 cs.AI 57%

Lumine: An Open Recipe for Building Generalist Agents in 3D Open Worlds

Weihao Tan, Xiangyang Li, Yunhao Fang, Heyuan Yao, Shi Yan, Hao Luo, Tenglong Ao, Huihui Li, Hongbin Ren, Bairen Yi, Yujia Qin, Bo An, Libin Liu, Guang Shi

机构 * ByteDance Seed（字节跳动种子）； NTU（国立科技大学）

专题命中视觉空间推理：reasoning(abstract)；分类 cs.AI

2511.08971 2025-11-13 cs.HC cs.CV cs.MM 50%

Plug-and-Play Clarifier: A Zero-Shot Multimodal Framework for Egocentric Intent Disambiguation

Sicheng Yang, Yukai Huang, Weitong Cai, Shitong Sun, You He, Jiankang Deng, Hang Zhang, Jifei Song, Zhensong Zhang

专题命中视觉空间推理：reasoning(abstract)

Comments 16 pages, 9 figures, AAAI 2026

2508.02557 2025-11-13 eess.IV cs.CV 50%

RL-U$^2$Net: A Dual-Branch UNet with Reinforcement Learning-Assisted Multimodal Feature Fusion for Accurate 3D Whole-Heart Segmentation

Jierui Qu, Jianchun Zhao

专题命中视觉空间推理：planning(abstract)

2406.17582 2025-11-13 cs.HC cs.GR cs.MM 50%

Crafting Dynamic Virtual Activities with Advanced Multimodal Models

Changyang Li, Qingan Yan, Minyoung Kim, Zhan Li, Yi Xu, Lap-Fai Yu

专题命中视觉空间推理：reasoning(abstract)

Journal ref C. Li, Q. Yan, M. Kim, Z. Li, Y. Xu and L. -F. Yu, "Crafting Dynamic Virtual Activities with Advanced Multimodal Models," 2025 IEEE International Symposium on Mixed and Augmented Reality (ISMAR), pp. 120-130