Latent Visual Reasoning

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 69

All topics

Self-Consistent Latent Reasoning: Long Latent Sequence Reasoning for Vision-Language Model
May 12, 2026Chenfeng Wang, Wei He, Xuhan Zhu +10Visual Reasoning Latent Visual Reasoning
University of Science and Technology of China · Li Auto Inc.
UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs
May 12, 2026Houcheng Jiang, Jiajun Fu, Junfeng Fang +4Efficient Multimodal Inference Multimodal Large Language Models
University of Science and Technology of China · Zhongguancun Academy · National University of Singapore +1
CoLVR: Enhancing Exploratory Latent Visual Reasoning via Contrastive Optimization
May 9, 2026Ziyang Ding, Linjian Meng, Yiming Wu +3Visual Reasoning Latent Visual Reasoning
Shandong University · Shanghai AI Laboratory · Nanjing University +1
Retrieve, Integrate, and Synthesize: Spatial-Semantic Grounded Latent Visual Reasoning
May 8, 2026Jin Cui, Xinyue Long, Xunyong Zhang +5Visual Spatial Reasoning Visual Reasoning
1State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, and Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University · School of Software Engineering, State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University
Visual Latents Know More Than They Say: Unsilencing Latent Reasoning in MLLMs
May 4, 2026Xin Zhang, Qiqi Tao, Jiawei Du +2Inference-Time Optimization Test-Time Optimization
Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore · Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore · Singapore University of Technology and Design +1
HyLaR: Hybrid Latent Reasoning with Decoupled Policy Optimization
Apr 22, 2026Tao Cheng, Shi-Zhe Chen, Hao Zhang +3Multimodal Large Language Models Multimodal Reasoning
Tencent PCG, China · Tencent CSIG, China
Decompose, Look, and Reason: Reinforced Latent Reasoning for VLMs
Apr 8, 2026Mengdan Zhu, Senhao Cheng, Liang ZhaoVLM Interpretability Latent Visual Reasoning
Emory University · University of Michigan, Ann Arbor
Imagination Helps Visual Reasoning, But Not Yet in Latent Space
Feb 26, 2026You Li, Chi Chen, Yanghao Li +4Causal Mediation Analysis Visual Reasoning
School of Computer Science and Technology, Beijing Jiao-tong University · Key Laboratory of Big Data & Artificial Intelli-gence in Transportation (Beijing Jiaotong University), Ministry of Education · Tsinghua University
Reason Through the Latent! Making Latent Visual Reasoning Necessary
Date pendingSuhyeong Park, Junha Jung, Jaewoo KangVisual Reasoning Multimodal Reasoning
Korea University · AIGEN Sciences

May 12, 2026, cs.CVJ/K move · Enter open · S save

Self-Consistent Latent Reasoning: Long Latent Sequence Reasoning for Vision-Language Model

Chenfeng Wang, Wei He, Xuhan Zhu, Chunpeng Zhou+9

University of Science and Technology of China · Li Auto Inc.

Visual Reasoning Latent Visual Reasoning VLM Reasoning Visually Grounded Reasoning

Open paper AskPDF arXiv

In language reasoning, longer chains of thought consistently yield better performance, which naturally suggests that visual latent reasoning may likewise benefit from longer latent sequences. However, we discover a counterintuitive phenomenon: the performance of existing latent visual reasoning methods systematically degrades as the latent sequence grows longer. We reveal the root cause: Information Gain Collapse -- autoregressive generation makes each step highly dependent on prior outputs, so subsequent tokens can barely introduce new information. We further identify that heavily pooled (

\geq 128\times

) image embeddings used as supervision targets provide no more signal than meaningless placeholders. Motivated by these insights, we propose SCOLAR (Self-COnsistent LAtent Reasoning), which introduces a lightweight detransformer that leverages the LLM's full-sequence hidden states to generate auxiliary visual tokens in a single shot, with each token independently anchored to the original visual space. Combined with three-stage SFT and ALPO reinforcement learning, SCOLAR extends acceptable latent CoT length by over

30\times

, achieves state-of-the-art among open-source models on real-world reasoning benchmarks (+14.12% over backbone), and demonstrates strong out-of-distribution generalization.

Momentum

Related topics

Latest papers 69