大模型推理能力

OpenCity: Open Spatio-Temporal Foundation Models for Traffic Prediction

Zhonghang Li, Long Xia, Lei Shi, Yong Xu, Dawei Yin, Chao Huang

机构 * The University of Hong Kong（香港大学） ； South China University of Technology（华南理工大学） ； Baidu Inc.（百度公司） 纠错

专题命中 规划推理 ：planning(abstract)；分类 cs.AI、cs.LG

Comments 12 pages

Journal ref ACM TIST, 2025

Dynamics-Decoupled Trajectory Alignment for Sim-to-Real Transfer in Reinforcement Learning for Autonomous Driving

Thomas Steinecker, Alexander Bienemann, Denis Trescher, Thorsten Luettel, Mirko Maehlisch

机构 * University of the Bundeswehr Munich（联邦国防军慕尼黑大学） 纠错

专题命中 规划推理 ：planning(abstract)；分类 cs.LG

LLM Driven Processes to Foster Explainable AI

Marcel Pehlke, Marc Jansen

机构 * University of Applied Sciences Ruhr West（鲁尔西部应用科学大学） 纠错

专题命中 规划推理 ：reasoning(abstract)；分类 cs.AI

Coupling Agent-based Modeling and Life Cycle Assessment to Analyze Trade-offs in Resilient Energy Transitions

Beichen Zhang, Mohammed T. Zaki, Hanna Breunig, Newsha K. Ajami

机构 * Lawrence Berkeley National Laboratory（伯克利劳伦斯国家实验室） 纠错

专题命中 规划推理 ：planning(abstract)；分类 cs.LG

Comments 4 pages (+4 pages in appendix), 3 figures (+ 2 figures in appendix), 8 tables in appendix, NeurIPS Workshop on Tackling Climate Change with Machine Learning, 2025

Beyond Resolution: Multi-Scale Weather and Climate Data for Alpine Renewable Energy in the Digital Twin Era -- First Evaluations and Recommendations

Irene Schicker, Marianne Bügelmayer-Blaschek, Annemarie Lexer, Katharina Baier, Kristofer Hasel, Paolo Gazzaneo

专题命中 规划推理 ：planning(abstract)；分类 cs.LG

Comments perspectives paper submitted to iScience, 25 pages, 2 tables, 3 figures

Journal ref iScience 2025

Interpreting Multi-Attribute Confounding through Numerical Attributes in Large Language Models

Hirohane Takagi, Gouki Minegishi, Shota Kizawa, Issey Sukeda, Hitomi Yanaka

机构 * The University of Tokyo（东京大学） ； RIKEN（日本研究机构） ； Tohoku University（东北大学） 纠错

专题命中 规划推理 ：reasoning(abstract)；分类 cs.AI

Comments Accepted to IJCNLP-AACL 2025 (Main). Code available at https://github.com/htkg/num_attrs

DeepDiver: Adaptive Search Intensity Scaling via Open-Web Reinforcement Learning

Wenxuan Shi, Haochen Tan, Chuqiao Kuang, Xiaoguang Li, Xiaozhe Ren, Chen Zhang, Hanting Chen, Yasheng Wang, Lu Hou, Lifeng Shang

机构 * Huawei Language Model Lab（华为语言模型实验室） 纠错

专题命中 规划推理 ：reasoning(abstract)；分类 cs.CL

Comments Accepted as NeurIPS 2025 Spotlight

BLADE: Benchmarking Language Model Agents for Data-Driven Science

Ken Gu, Ruoxi Shang, Ruien Jiang, Keying Kuang, Richard-John Lin, Donghe Lyu, Yue Mao, Youran Pan, Teng Wu, Jiaqian Yu, Yikun Zhang, Tianmai M. Zhang, Lanyi Zhu, Mike A. Merrill, Jeffrey Heer, Tim Althoff

机构 * University of Washington（华盛顿大学） ； UC Berkeley（伯克利大学） ； New York University（纽约大学） ； Stanford University（斯坦福大学） ； University of British Columbia（不列颠哥伦比亚大学） ； Microsoft（微软） ； George Washington University（乔治·华盛顿大学） 纠错

专题命中 规划推理 ：planning(abstract)；分类 cs.CL

Comments EMNLP 2024

MemoriesDB: A Temporal-Semantic-Relational Database for Long-Term Agent Memory / Modeling Experience as a Graph of Temporal-Semantic Surfaces

Joel Ward

机构 * CircleClick Labs（CircleClick实验室） 纠错

专题命中 规划推理 ：reasoning(abstract)；分类 cs.AI

UniMove: A Unified Model for Multi-city Human Mobility Prediction

Chonghua Han, Yuan Yuan, Yukun Liu, Jingtao Ding, Jie Feng, Yong Li

机构 * Department of Electronic Engineering, BNRist, Tsinghua University, Beijing, China（电子工程系，BNRist，清华大学，北京，中国） 纠错

专题命中 规划推理 ：planning(abstract)；分类 cs.LG

Comments Accepted by SIGSPATIAL 2025

PlanT 2.0: Exposing Biases and Structural Flaws in Closed-Loop Driving

Simon Gerstenecker, Andreas Geiger, Katrin Renz

机构 * University of Tübingen（图宾根大学） ； Tübingen AI Center（图宾根人工智能中心） 纠错

专题命中 规划推理 ：planning(abstract)

Multi-Agent Reinforcement Learning for Deadlock Handling among Autonomous Mobile Robots

Marcel Müller

专题命中 规划推理 ：planning(abstract)

Comments for associated repositories, see https://github.com/Nerozud/dl_reference_models and https://github.com/Nerozud/FTS_simpel

AdaDrive: Self-Adaptive Slow-Fast System for Language-Grounded Autonomous Driving

Ruifei Zhang, Junlin Xie, Wei Zhang, Weikai Chen, Xiao Tan, Xiang Wan, Guanbin Li

机构 * The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）） ； Shenzhen Research Institute of Big Data（深圳大数据研究院） ； Sun Yat-sen University（中山大学） ； Baidu Inc.（百度公司） ； Guangdong Key Laboratory of Big Data Analysis and Processing（广东大数据分析与处理重点实验室） 纠错

专题命中 规划推理 ：reasoning(abstract)

Comments Accepted by ICCV2025

In-Context-Learning-Assisted Quality Assessment Vision-Language Models for Metal Additive Manufacturing

Qiaojie Zheng, Jiucai Zhang, Xiaoli Zhang

机构 * Colorado School of Mines（科罗拉多矿业学院） 纠错

专题命中 规划推理 ：reasoning(abstract)

Comments 8 pages, 8 figures

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/

The Energy Cost of Reasoning: Analyzing Energy Usage in LLMs with Test-time Compute

Yunho Jin, Gu-Yeon Wei, David Brooks

机构 * Harvard University（哈佛大学） 纠错

专题命中 测试时计算 ：reasoning(title,abstract)；test-time compute(title,abstract)；分类 cs.AI、cs.LG

Rank-1 LoRAs Encode Interpretable Reasoning Signals

Jake Ward, Paul Riechers, Adam Shai

机构 * MATS 纠错

专题命中 测试时计算 ：reasoning(title,abstract)；分类 cs.AI、cs.LG

Comments 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: Mechanistic Interpretability Workshop