Cover Image

Multi-Step Visual Reasoning with Visual Tokens Scaling and Verification

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bai, Tianyi, Hu, Zengjie, Sun, Fupeng, Qiu, Jiantao, Jiang, Yizhen, He, Guangxin, Zeng, Bohan, He, Conghui, Yuan, Binhang, Zhang, Wentao
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Hallucination at a Glance: Controlled Visual Edits and Fine-Grained Multimodal Learning
by: Bai, Tianyi, et al.
Published: (2025)

Efficient Pretraining Data Selection for Language Models via Multi-Actor Collaboration
by: Bai, Tianyi, et al.
Published: (2024)

VADE: Variance-Aware Dynamic Sampling via Online Sample-Level Difficulty Estimation for Multimodal RL
by: Hu, Zengjie, et al.
Published: (2025)

Synthesizing Multimodal Geometry Datasets from Scratch and Enabling Visual Alignment via Plotting Code
by: Lin, Haobo, et al.
Published: (2026)

TQA-Bench: Evaluating LLMs for Multi-Table Question Answering with Scalable Context and Symbolic Extension
by: Qiu, Zipeng, et al.
Published: (2024)

UltraLLaDA: Scaling the Context Length to 128K for Diffusion Large Language Models
by: He, Guangxin, et al.
Published: (2025)

From Tokens to Steps: Verification-Aware Speculative Decoding for Efficient Multi-Step Reasoning
by: Purohit, Kiran, et al.
Published: (2026)

Meta-rater: A Multi-dimensional Data Selection Method for Pre-training Language Models
by: Zhuang, Xinlin, et al.
Published: (2025)

Native Visual Understanding: Resolving Resolution Dilemmas in Vision-Language Models
by: Niu, Junbo, et al.
Published: (2025)

Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning
by: Wang, Bohan, et al.
Published: (2025)

VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models
by: Li, Zejun, et al.
Published: (2024)

TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos
by: Feng, Hengyi, et al.
Published: (2026)

Factorized Visual Tokenization and Generation
by: Bai, Zechen, et al.
Published: (2024)

BLINK-Twice: You see, but do you observe? A Reasoning Benchmark on Visual Perception
by: Ye, Junyan, et al.
Published: (2025)

Dripper: Token-Efficient Main HTML Extraction with a Lightweight LM
by: Liu, Mengjie, et al.
Published: (2025)

TAH-QUANT: Effective Activation Quantization in Pipeline Parallelism over Slow Network
by: He, Guangxin, et al.
Published: (2025)

Topic Over Source: The Key to Effective Data Mixing for Language Models Pre-training
by: Peng, Jiahui, et al.
Published: (2025)

Heterogeneous Adaptive Policy Optimization: Tailoring Optimization to Every Token's Nature
by: Liu, Zheng, et al.
Published: (2025)

ExoViP: Step-by-step Verification and Exploration with Exoskeleton Modules for Compositional Visual Reasoning
by: Wang, Yuxuan, et al.
Published: (2024)

TCFormer: Visual Recognition via Token Clustering Transformer
by: Zeng, Wang, et al.
Published: (2024)

A Survey of Multimodal Large Language Model from A Data-centric Perspective
by: Bai, Tianyi, et al.
Published: (2024)

ConfSpec: Efficient Step-Level Speculative Reasoning via Confidence-Gated Verification
by: Liu, Siran, et al.
Published: (2026)

Focus-Scan-Refine: From Human Visual Perception to Efficient Visual Token Pruning
by: Tong, Enwei, et al.
Published: (2026)

Fourier Compressor: Frequency-Domain Visual Token Compression for Vision-Language Models
by: Wang, Huanyu, et al.
Published: (2025)

PixelCraft: A Multi-Agent System for High-Fidelity Visual Reasoning on Structured Images
by: Zhang, Shuoshuo, et al.
Published: (2025)

Robust Camera-to-Mocap Calibration and Verification for Large-Scale Multi-Camera Data Capture
by: Liu, Tianyi, et al.
Published: (2026)

Let's Verify Math Questions Step by Step
by: Shen, Chengyu, et al.
Published: (2025)

TAG: Thinking with Action Unit Grounding for Facial Expression Recognition
by: Lin, Haobo, et al.
Published: (2026)

OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation
by: Wang, Junke, et al.
Published: (2024)

Analyzing The Language of Visual Tokens
by: Chan, David M., et al.
Published: (2024)

Beyond the Last Layer: Multi-Layer Representation Fusion for Visual Tokenization
by: Zhu, Xuanyu, et al.
Published: (2026)

Beyond Embeddings: The Promise of Visual Table in Visual Reasoning
by: Zhong, Yiwu, et al.
Published: (2024)

Evaluating Step-by-Step Reasoning through Symbolic Verification
by: Zhang, Yi-Fan, et al.
Published: (2022)

How Far Are We from Intelligent Visual Deductive Reasoning?
by: Zhang, Yizhe, et al.
Published: (2024)

Why 1 + 1 < 1 in Visual Token Pruning: Beyond Naive Integration via Multi-Objective Balanced Covering
by: Li, Yangfu, et al.
Published: (2025)

Neighboring Autoregressive Modeling for Efficient Visual Generation
by: He, Yefei, et al.
Published: (2025)

Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem?
by: Wen, Zichen, et al.
Published: (2025)

Textual-to-Visual Iterative Self-Verification for Slide Generation
by: Xu, Yunqing, et al.
Published: (2025)

Structure Over Scale: Learning Visual Reasoning from Pedagogical Video
by: Galoaa, Bishoy, et al.
Published: (2026)

Schedule-Level Shared-Prefix Reuse for LLM RL Training
by: Li, Pengbo, et al.
Published: (2026)