Pith. sign in

REVIEW 12 cited by

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.05331 v1 pith:DWUNFJGV submitted 2025-06-05 cs.CV

MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning

classification cs.CV
keywords visualreasoningmathematicalmint-cotinterleavedchain-of-thoughtmathregions
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Chain-of-Thought (CoT) has widely enhanced mathematical reasoning in Large Language Models (LLMs), but it still remains challenging for extending it to multimodal domains. Existing works either adopt a similar textual reasoning for image input, or seek to interleave visual signals into mathematical CoT. However, they face three key limitations for math problem-solving: reliance on coarse-grained box-shaped image regions, limited perception of vision encoders on math content, and dependence on external capabilities for visual modification. In this paper, we propose MINT-CoT, introducing Mathematical INterleaved Tokens for Chain-of-Thought visual reasoning. MINT-CoT adaptively interleaves relevant visual tokens into textual reasoning steps via an Interleave Token, which dynamically selects visual regions of any shapes within math figures. To empower this capability, we construct the MINT-CoT dataset, containing 54K mathematical problems aligning each reasoning step with visual regions at the token level, accompanied by a rigorous data generation pipeline. We further present a three-stage MINT-CoT training strategy, progressively combining text-only CoT SFT, interleaved CoT SFT, and interleaved CoT RL, which derives our MINT-CoT-7B model. Extensive experiments demonstrate the effectiveness of our method for effective visual interleaved reasoning in mathematical domains, where MINT-CoT-7B outperforms the baseline model by +34.08% on MathVista, +28.78% on GeoQA, and +23.2% on MMStar, respectively. Our code and data are available at https://github.com/xinyan-cxy/MINT-CoT

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Optical Reasoning: Rethinking Images as an Expressive Reasoning Medium Beyond Text

    cs.AI 2026-06 unverdicted novelty 7.0

    Optical reasoning encodes rationales in images rather than text, matching or exceeding text-based performance on math, science, and multimodal benchmarks while cutting tokens by 28.57% on language tasks and 16% on mul...

  2. MuCRASP: Multimodal Chain-of-thought Reasoning aware Structured Pruning

    cs.AI 2026-05 unverdicted novelty 7.0

    MuCRASP prunes VLMs in a CoT-aware manner, outperforming baselines by preserving reasoning quality at 30-50% compression rates on models like Qwen2.5-VL-7B.

  3. Omni-R1: Towards the Unified Generative Paradigm for Multimodal Reasoning

    cs.AI 2026-01 unverdicted novelty 7.0

    Omni-R1 unifies multimodal reasoning by generating intermediate images during the process in a SFT-plus-RL framework, with an Omni-R1-Zero variant that matches or exceeds it using only text data.

  4. OpenCoF: Learning to Reason Through Video Generation

    cs.CV 2026-07 conditional novelty 6.0

    Fine-tuning a video generator on a new 17K reasoning-video dataset improves Chain-of-Frame reasoning, and adding learnable visual/textual reasoning tokens yields further gains on external benchmarks.

  5. Multimodal Continuous Reasoning via Asymmetric Mutual Variational Learning

    cs.CV 2026-07 unverdicted novelty 6.0

    AMVL applies bidirectional KL calibration to align answer-agnostic prior with answer-conditioned posterior in variational multimodal reasoning, reducing leakage and yielding +10.83 average gain on BLINK benchmark.

  6. Latent Noise Mask for Reducing Visual Redundancy in Multimodal Large Language Models

    cs.CV 2026-06 unverdicted novelty 6.0

    Lens purifies visual evidence in MLLMs via question-conditioned latent noise masking with a LET token, yielding 2.4-6.4 point gains on VQA and grounding tasks.

  7. ROVER: Routing Object-Centric Visual Evidence for Grounded Multi-Image Reasoning

    cs.CV 2026-05 unverdicted novelty 6.0

    ROVER introduces a learnable routing plugin for object-centric visual evidence in MLLMs via token triplets and differential attention, reporting gains on MM-GCoT and VideoEspresso when integrated into Qwen2.5-VL-7B.

  8. Latent Visual States for Efficient Multimodal Reasoning

    cs.CV 2026-06 unverdicted novelty 5.0

    EVA generates adaptive Latent_slot tokens as internal visual thoughts, trained end-to-end with text tokens via D-GSPO on the EVA-230K dataset, claiming performance gains and better inference efficiency.

  9. MathVis-Fine: Aligning Visual Supervision with Necessity via Progressive Dependency-Guided Training for Multimodal Mathematical Reasoning

    cs.AI 2026-06 unverdicted novelty 5.0

    MathVis-Fine proposes a dataset with fine-grained visual annotations and dependency ratings plus a progressive two-stage training paradigm to align visual supervision with sample-specific necessity in multimodal mathe...

  10. UniReason-Med: A Shared Grounded Reasoning Interface for 2D-to-3D Transfer in Medical VQA

    cs.CV 2026-06 unverdicted novelty 4.0

    UniReason-Med introduces a unified framework for 2D and 3D medical VQA with shared grounded reasoning, trained on a 220K dataset, claiming that joint 2D+3D supervision improves 3D performance over 3D-only training.

  11. Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI

    cs.AI 2025-10 unverdicted novelty 4.0

    A survey of physical AI that distinguishes theoretical physics reasoning from applied understanding and synthesizes advances in symbolic reasoning, embodied systems, and generative models to advocate for physics-groun...

  12. Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discovery

    cs.AI 2026-06 unverdicted novelty 3.0

    An integrated survey organizing AI mathematical reasoning into informal, formal, discovery, and technique axes while cataloging benchmarks and assessing failure modes.