大模型推理能力

EVLM: Self-Reflective Multimodal Reasoning for Cross-Dimensional Visual Editing

Umar Khalid, Kashif Munir, Hasan Iqbal, Azib Farooq, Jing Hua, Nazanin Rahnavard, Chen Chen, Victor Zhu, Zhengping Ji

专题命中 视觉空间推理 ：reasoning(title,abstract)；chain-of-thought(abstract)；CoT(abstract)

Comments Technical Report

Visual Structures Helps Visual Reasoning: Addressing the Binding Problem in VLMs

Amirmohammad Izadi, Mohammad Ali Banayeeanzade, Fatemeh Askari, Ali Rahimiakbar, Mohammad Mahdi Vahedi, Hosein Hasani, Mahdieh Soleymani Baghshah

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

Comments Accepted to NeurIPS 2025 (Thirty-ninth Conference on Neural Information Processing Systems)

Open-World 3D Scene Graph Generation for Retrieval-Augmented Reasoning

Fei Yu, Quan Deng, Shengeng Tang, Yuehua Li, Lechao Cheng

专题命中 视觉空间推理 ：reasoning(title,abstract)；planning(abstract)

Comments Accepted by AAAI 2026

ASTER: Attention-based Spiking Transformer Engine for Event-driven Reasoning

Tamoghno Das, Khanh Phan Vu, Hanning Chen, Hyunwoo Oh, Mohsen Imani

专题命中 视觉空间推理 ：reasoning(title,abstract)

Comments Submitted for review at conference

MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentation

Jiaxin Huang, Runnan Chen, Ziwen Li, Zhengqing Gao, Xiao He, Yandong Guo, Mingming Gong, Tongliang Liu

机构 * MBZUAI ； The University of Sydney（悉尼大学） ； The University of Melbourne（墨尔本大学） ； AI2Robotic 纠错

专题命中 视觉空间推理 ：reasoning(title,abstract)

Comments 10 pages, 3 figures

BuildingWorld: A Structured 3D Building Dataset for Urban Foundation Models

Shangfeng Huang, Ruisheng Wang, Xin Wang

专题命中 视觉空间推理 ：reasoning(abstract)；planning(abstract)

Federated Learning for Video Violence Detection: Complementary Roles of Lightweight CNNs and Vision-Language Models for Energy-Efficient Use

Sébastien Thuau, Siba Haidar, Rachid Chelouah

机构 * esieaLab, ETIS Laboratory（esiea实验室，ETIS实验室） ； ESIEA, University of CY Cergy（ESIEA，CY塞克大学） ； ETIS Laboratory, CNR1S, UMR8051（ETIS实验室，CNR1S，UMR8051） 纠错

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

Comments 5 pages, 3 figures, ICTAI 2025

Referring Expressions as a Lens into Spatial Language Grounding in Vision-Language Models

Akshar Tumu, Varad Shinde, Parisa Kordjamshidi

机构 * UC San Diego（加州大学圣地亚哥分校） ； IIT Kanpur（印度理工学院坎pur） ； Michigan State University（密歇根州立大学） 纠错

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

Comments Accepted at IJCNLP-AACL 2025

Hybrid CNN-ViT Framework for Motion-Blurred Scene Text Restoration

Umar Rashid, Muhammad Arslan Arshad, Ghulam Ahmad, Muhammad Zeeshan Anjum, Rizwan Khan, Muhammad Akmal

机构 * Department of Electrical Engineering, University of Engineering & Technology, New Campus, Lahore, Pakistan（电子工程系，工程科技大学，新校区，拉合尔，巴基斯坦） ； Department of Electrical, Electronic, and Future Technologies, Sheffield Hallam University, Sheffield S1 1WB, UK（电子、电气与未来技术系，谢菲尔德哈姆大学，谢菲尔德 S1 1WB，英国） 纠错

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

Controllable Hybrid Captioner for Improved Long-form Video Understanding

Kuleen Sasse, Efsun Sarioglu Kayi, Arun Reddy

机构 * Johns Hopkins University Applied Physics Laboratory（约翰霍普金斯大学应用物理实验室） 纠错

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

VideoCAD: A Dataset and Model for Learning Long-Horizon 3D CAD UI Interactions from Video

Brandon Man, Ghadi Nehme, Md Ferdous Alam, Faez Ahmed

机构 * Massachusetts Institute of Technology（麻省理工学院） 纠错

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

PanoNav: Mapless Zero-Shot Object Navigation with Panoramic Scene Parsing and Dynamic Memory

Qunchao Jin, Yilin Wu, Changhao Chen

专题命中 视觉空间推理 ：reasoning(abstract)

Comments Accepted as a poster in AAAI 2026

Scene-Aware Urban Design: A Human-AI Recommendation Framework Using Co-Occurrence Embeddings and Vision-Language Models

Rodrigo Gallardo, Oz Fishman, Alexander Htet Kyaw

机构 * Department of Architecture（建筑系） ； Department of EECS（电子工程与计算机科学系） ； Massachusetts Institute of Technology（麻省理工学院） 纠错

专题命中 视觉空间推理 ：planning(abstract)

Comments Accepted to NEURIPS 2025 Creative AI Track

FreeInsert: Disentangled Text-Guided Object Insertion in 3D Gaussian Scene without Spatial Priors

Chenxi Li, Weijie Wang, Qiang Li, Bruno Lepri, Nicu Sebe, Weizhi Nie

机构 * Tianjin University（天津大学） ； University of Trento（特伦托大学） 纠错

专题命中 视觉空间推理 ：reasoning(abstract)

Comments Accepted by ACMMM2025, Our project webpage: https://tjulcx.github.io/FreeInsert/