Think

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 37

All topics

MG-Thinker: Bi-Axial Self-Reflection for Multi-Image Reasoning Grounding
Sep 29, 2026Heyu Huang, Chi Chen, Zonghao Guo +3Multi-Turn Reinforcement Learning Multi-Agent Reasoning
Huazhong University of Science and Technology Wuhan, China · Tsinghua University Beijing, China
Think Before You Score: Thinking Reward Model for Visual Generation
Sep 29, 2026Xuehai Bai, Zhenchen Tang, Yang Shi +9Progress Reward Modeling Visual Generation
HDU · SenseTime · CASIA +5
ThinkingGuard: Decoding Implicit Hazards via Step-by-Step Risk Attribution in Multimodal Large Language Models
Sep 29, 2026Ruochen Zhang, Yao Huang, Yitong Sun +5Large Language Model Safety Multimodal Large Language Models
Beihang University Beijing, China · Tsinghua University Beijing, China · Institute of Artificial Intelligence Beihang University Beijing, China State Key Laboratory of AI Safety
RetroThinker: Enabling Retrospective Thinking in Speech LLMs
Sep 12, 2026Yi-Jen Shih, Puyuan Peng, Abdelrahman Mohamed +1LLM Reasoning Strategies Speech Language Models
The University of Texas at Austin · FAIR, Meta Superintelligence Labs
</think> Doesn't Stop Reasoning: Analysis of Spurious CoT Termination
Sep 3, 2026Seunghee Koh, Sungjae Choi, Minchan Kwon +2Chain-of-Thought Reasoning Think
Korea Advanced Institute of Science and Technology, South Korea
Enhancing Virtual Agents through SLMs and Edge-Computing: An Exploratory Evaluation of Think and Memory Processes
Aug 13, 2026Aimilios Hadjiliasi, Louis NisiotisEmbodied Agents Edge Devices
Department of Computing, Engineering and Mathematics University of Central Lancashire, Cyprus
AdaThinkV: Adaptive Thinking for Token-Efficient Video Reasoning
Aug 3, 2026Jingqi Tian, Haoji Zhang, Lin Chen +7Think
Tsinghua Shenzhen International Graduate School, Tsinghua University · Alibaba Group · Peking University
See2Think: Do Multimodal Models Really Use Intermediate Visual States?
Jul 29, 2026Siyu Yan, Zhuoran Yan, Haiying Xu +10Large Multimodal Models Multimodal Model
1The Hong Kong University of Science and Technology · 3Shanghai AI Laboratory · 2Central South University +4
Thinkink: 2D Spatial Ink-native Interaction with LLMs
Jul 23, 2026Mohammad Hasan Payandeh, Daniel Vogel, Jian ZhaoThink Handwriting
Cheriton School of Computer Science, University of Waterloo Waterloo, Canada
TreeThink: A Modular Tree Search Library for Mathematical Reasoning with LLMs
Jul 13, 2026Burak S. Akbudak, Zeynel A. Uluşan, Can S. Erer +1Theorem Proving Tree Search
Computer Engineering Department, Bogazici University, Istanbul, Turkey · Computer Engineering Department, Koç University, Istanbul, Turkey · Codeway Studios, Istanbul, Turkey +2
MentalThink: Shaping Thoughts in Mental SVG World
Jul 3, 2026Kangheng Lin, Jisheng Yin, Dingming Li +11Think Imagination
State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications · University of Chinese Academy of Sciences · StepFun
Fork-Think with Confidence
Jun 30, 2026Zena Al-Khalili, Rafi Hakim, Dietrich Klakow +1Think Thoughts
Saarland Informatics Campus, Saarland University, Germany
MIThinker: A Plug-and-Play Policy-Optimized Thinker For Motivational Interviewing Counseling
Jun 28, 2026Yizhe Yang, Palakorn Achananuparp, Heyan Huang +2Counseling Think
Beijing Institute of Technology · Singapore Management University · Australian National University
Think Again or Think Longer? Selective Verification for Budget-Aware Reasoning
Jun 18, 2026Sajib Acharjee Dip, Dawei Zhou, Liqing ZhangToken Budget Allocation Think
Department of Computer Science, Virginia Tech · Fralin Biomedical Research Institute, Virginia Tech · FBRI Cancer Research Center, Washington, DC
SuperThoughts: Reasoning Tokens in Superposition
Jun 11, 2026Zheyang Xiong, Shivam Garg, Max Yu +4Chain-of-Thought Reasoning Think
mMicrosoft Research · iIndependent · pPrinceton University +2
TouchThinker: Scaling Tactile Commonsense Reasoning to the Open World with Large-scale Data and Action-aware Representation
Jun 10, 2026Kailin Lyu, Di Wu, Pengwei Zhang +12Open-World Think
Institute of Automation, Chinese Academy of Sciences · Zhongguancun Academy · National University of Singapore +4
Think Fast: Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models
Jun 5, 2026Dewi Gould, Francis Rhys Ward, Anders Cairns Woodruff +18Frontier Models Large Reasoning Models
Redwood Research · Astra Fellows Program · Aether Research +10
OneReason Technical Report
Jun 4, 2026OneRec Team, Biao Yang, Boyang Ding +81Think Reasoning Skills
Rotate2Think: Geometric Priming via Orthogonal Rotation to Improve Language Model Reasoning
Jun 2, 2026Aditya Sharma, Christopher J. Pal, Amal ZouaqLarge Reasoning Models Think
Polytechnique Montréal · Mila - Quebec AI Institute · LAMA-WeST Lab +1
GeneralThinker: Domain-General Reasoning through Likelihood-Guided Answer-Conditioned Optimization
May 27, 2026Shengmin Piao, Sanghyun ParkThink Credit Assignment
Yonsei University Seoul, South Korea
Test-Time Deep Thinking to Explore Implicit Rules
May 24, 2026Wentong Chen, Xin Cong, Zhong Zhang +8Agentic Reasoning Reasoning Trajectory
Renmin University of China Beijing, China · Department of Statistics and Data Science, Tsinghua University Beijing, China · School of Computer Science and Engineering, UESTC Chengdu, China +4
Draw2Think: Harnessing Geometry Reasoning through Constraint Engine Interaction
May 20, 2026Juncheng Hu, Jiawei Du, Xin Zhang +1Geometric Constraints Think
National University of Singapore, Singapore · Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore · Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore
Taming the Thinker: Conditional Entropy Shaping for Adaptive LLM Reasoning
May 19, 2026Shuyu Wei, Jian Sun, Delai Qiu +6LLM Reasoning Strategies Token-Level Entropy
Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, Beijing Jiaotong University · Unisound AI Technology Co., Ltd.
Guide, Think, Act: Interactive Embodied Reasoning in Vision-Language-Action Models
May 13, 2026Yiran Ling, Qing Lian, Jinghang Li +6Geometric Guidance Action Expert
Faculty of Computing, Harbin Institute of Technology · International Digital Economy Academy (IDEA) · National Key Laboratory of Smart Farm Technologies and Systems +4
RadThinking: A Dataset for Longitudinal Clinical Reasoning in Radiology
May 11, 2026Wenxuan Li, Pedro R. A. S. Bassi, Xinze Zhou +3Medical Visual Question Answering Reasoning Skills
Department of Computer Science, Johns Hopkins University · Clinic of Radiology and Nuclear Medicine, University Hospital Basel · Department of Oncology, Johns Hopkins School of Medicine
ExpThink: Experience-Guided Reinforcement Learning for Adaptive Chain-of-Thought Compression
May 8, 2026Tingcheng Bian, Yuzhe Zhang, Jing Jin +5Large Reasoning Models Chain-of-Thought Reasoning
1Baidu Inc. · 2Shenzhen University · 3Peking University +2
Pest-Thinker: Learning to Think and Reason like Entomologists via Reinforcement Learning
May 7, 2026Xueheng Li, Yu Wang, Tao Hu +6Bees Fine-Grained Perception
Institute of Intelligent Machines, Hefei Institute of Physical Science, Chinese Academy of Sciences · University of Science and Technology of China · 4Hefei University of Technology +1
Think, then Score: Decoupled Reasoning and Scoring for Video Reward Modeling
May 7, 2026Yuan Wang, Ouxiang Li, Yulong Xu +8Generative Video Models Scoring
University of Science and Technology of China · Kling Team, Kuaishou Technology · Institute of Software Chinese Academy of Sciences
Beyond Perceptual Shortcuts: Causal-Inspired Debiasing Optimization for Generalizable Video Reasoning in Lightweight MLLMs
May 2, 2026Jingze Wu, Quan Zhang, Hongfei Suo +2Video Understanding Multimodal Large Language Models
Sun Yat-sen University, China
Select to Think: Unlocking SLM Potential with Local Sufficiency
Apr 29, 2026Wenxuan Ye, Yangyang Zhang, Xueli An +2Small Large Language Models LLM Inference Optimization
1Technical University of Munich · 3Ludwig Maximilian University of Munich · 2Huawei Technologies +2
DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing
Apr 28, 2026Hanqing Yang, Qiang Zhou, Yongchao Du +6Image Editing Multi-Reference Image Generation
Alibaba Group · Zhejiang University
Learning to Think from Multiple Thinkers
Apr 27, 2026Nirmit Joshi, Roey Magen, Nathan Srebro +2Learnability Chain-of-Thought Reasoning
Toyota Technological Institute at Chicago. · Weizmann Institute of Science. · New York University.
ProcessThinker: Enhancing Multi-modal Large Language Models Reasoning via Rollout-based Process Reward
Apr 23, 2026Jingpei Wu, Xiao Han, Weixiang Shen +3Multimodal Reasoning Process Reward Model
LMU Munich · Harvard University · University of Cambridge +2
Think, Then Look: Active Spatial Reasoning for House-Scale 3D Scene Understanding
Dec 2, 2025Hongpei Zheng, Shijie Li, Lin Qian +43D Scene Understanding Spatial Reasoning
University of Manchester · Institute for Infocomm Research (I2R), A*STAR, Singapore · University of Bedfordshire
See, Think, Learn: A Self-Taught Multimodal Reasoner
Dec 2, 2025Sourabh Sharma, Sonam Gupta, SadbhawnaMultimodal Reasoning Recent Vision-Language Models
Malaviya National Institute of Technology Jaipur · IBM Research
PreferThinker: Reasoning-based Personalized Image Preference Assessment
Nov 1, 2025Shengqi Xu, Xinpeng Zhou, Yabo Zhang +6Preference Alignment Learning Think
♠Fudan University · ♣Harbin Institute of Technology · ♦iN2X
Think Right: Learning to Mitigate Under-Over Thinking via Adaptive, Attentive Compression
Oct 2, 2025Joykirat Singh, Justin Chih-Yao Chen, Archiki Prasad +3Large Reasoning Models Think
UNC Chapel Hill · The University of Texas at Austin · Microsoft Research

Sep 29, 2026, cs.CVJ/K move · Enter open · S save

MG-Thinker: Bi-Axial Self-Reflection for Multi-Image Reasoning Grounding

Heyu Huang, Chi Chen, Zonghao Guo, Yuhua Li+2

Huazhong University of Science and Technology Wuhan, China · Tsinghua University Beijing, China

Multi-Turn Reinforcement Learning Multi-Agent Reasoning Think Chain-of-Thought Reasoning

Open paper AskPDF arXiv

Reinforcement learning (RL) has recently delivered substantial gains in multimodal reasoning, opening a promising route for fine-grained visual perception. Yet for multi-image reasoning grounding (MRG), reasoning over real-world multi-image contexts toward pixel-precise localization, existing RL-based approaches overlook two characteristics intrinsic to this paradigm: a coarse-to-fine hierarchical reasoning pattern, and heterogeneously distributed task--sample difficulties. In this work, we present MG-Thinker, a post-training RL framework that advances a new MRG paradigm featuring such hierarchical reasoning, supported by a curated 25K MRG dataset with task-adaptive Chain-of-Thought (CoT) annotations that elicit multi-perspective evidence before conclusion. To remedy the heterogeneous task--sample difficulties, we further propose Bi-Axial DAPO (BiA-DAPO), which decomposes rollout advantages along an intra-group signal axis and an inter-group competence axis through two complementary mechanisms, both grounded on our defined candidate pool for stable group-level statistics. Extensive experiments show that MG-Thinker achieves state-of-the-art performance on multi-image reasoning grounding while consistently improving generalization across multi-image understanding and diverse multimodal benchmarks.

Momentum

Related topics

Latest papers 37