Close Menu
  • Home
  • AI Models
    • DeepSeek
    • xAI
    • OpenAI
    • Meta AI Llama
    • Google DeepMind
    • Amazon AWS AI
    • Microsoft AI
    • Anthropic (Claude)
    • NVIDIA AI
    • IBM WatsonX Granite 3.1
    • Adobe Sensi
    • Hugging Face
    • Alibaba Cloud (Qwen)
    • Baidu (ERNIE)
    • C3 AI
    • DataRobot
    • Mistral AI
    • Moonshot AI (Kimi)
    • Google Gemma
    • xAI
    • Stability AI
    • H20.ai
  • AI Research
    • Allen Institue for AI
    • arXiv AI
    • Berkeley AI Research
    • CMU AI
    • Google Research
    • Microsoft Research
    • Meta AI Research
    • OpenAI Research
    • Stanford HAI
    • MIT CSAIL
    • Harvard AI
  • AI Funding & Startups
    • AI Funding Database
    • CBInsights AI
    • Crunchbase AI
    • Data Robot Blog
    • TechCrunch AI
    • VentureBeat AI
    • The Information AI
    • Sifted AI
    • WIRED AI
    • Fortune AI
    • PitchBook
    • TechRepublic
    • SiliconANGLE – Big Data
    • MIT News
    • Data Robot Blog
  • Expert Insights & Videos
    • Google DeepMind
    • Lex Fridman
    • Matt Wolfe AI
    • Yannic Kilcher
    • Two Minute Papers
    • AI Explained
    • TheAIEdge
    • Matt Wolfe AI
    • The TechLead
    • Andrew Ng
    • OpenAI
  • Expert Blogs
    • François Chollet
    • Gary Marcus
    • IBM
    • Jack Clark
    • Jeremy Howard
    • Melanie Mitchell
    • Andrew Ng
    • Andrej Karpathy
    • Sebastian Ruder
    • Rachel Thomas
    • IBM
  • AI Policy & Ethics
    • ACLU AI
    • AI Now Institute
    • Center for AI Safety
    • EFF AI
    • European Commission AI
    • Partnership on AI
    • Stanford HAI Policy
    • Mozilla Foundation AI
    • Future of Life Institute
    • Center for AI Safety
    • World Economic Forum AI
  • AI Tools & Product Releases
    • AI Assistants
    • AI for Recruitment
    • AI Search
    • Coding Assistants
    • Customer Service AI
    • Image Generation
    • Video Generation
    • Writing Tools
    • AI for Recruitment
    • Voice/Audio Generation
  • Industry Applications
    • Finance AI
    • Healthcare AI
    • Legal AI
    • Manufacturing AI
    • Media & Entertainment
    • Transportation AI
    • Education AI
    • Retail AI
    • Agriculture AI
    • Energy AI
  • AI Art & Entertainment
    • AI Art News Blog
    • Artvy Blog » AI Art Blog
    • Weird Wonderful AI Art Blog
    • The Chainsaw » AI Art
    • Artvy Blog » AI Art Blog
What's Hot

Creating uniquely human digital banking experiences at TD

C3 AI Stock Plunges After ‘Completely Unacceptable’ Q1 Sales – C3.ai (NYSE:AI)

Meta says its Llama AI models being used by banks, tech companies

Facebook X (Twitter) Instagram
Advanced AI News
  • Home
  • AI Models
    • OpenAI (GPT-4 / GPT-4o)
    • Anthropic (Claude 3)
    • Google DeepMind (Gemini)
    • Meta (LLaMA)
    • Cohere (Command R)
    • Amazon (Titan)
    • IBM (Watsonx)
    • Inflection AI (Pi)
  • AI Research
    • Allen Institue for AI
    • arXiv AI
    • Berkeley AI Research
    • CMU AI
    • Google Research
    • Meta AI Research
    • Microsoft Research
    • OpenAI Research
    • Stanford HAI
    • MIT CSAIL
    • Harvard AI
  • AI Funding
    • AI Funding Database
    • CBInsights AI
    • Crunchbase AI
    • Data Robot Blog
    • TechCrunch AI
    • VentureBeat AI
    • The Information AI
    • Sifted AI
    • WIRED AI
    • Fortune AI
    • PitchBook
    • TechRepublic
    • SiliconANGLE – Big Data
    • MIT News
    • Data Robot Blog
  • AI Experts
    • Google DeepMind
    • Lex Fridman
    • Meta AI Llama
    • Yannic Kilcher
    • Two Minute Papers
    • AI Explained
    • TheAIEdge
    • The TechLead
    • Matt Wolfe AI
    • Andrew Ng
    • OpenAI
    • Expert Blogs
      • François Chollet
      • Gary Marcus
      • IBM
      • Jack Clark
      • Jeremy Howard
      • Melanie Mitchell
      • Andrew Ng
      • Andrej Karpathy
      • Sebastian Ruder
      • Rachel Thomas
      • IBM
  • AI Tools
    • AI Assistants
    • AI for Recruitment
    • AI Search
    • Coding Assistants
    • Customer Service AI
  • AI Policy
    • ACLU AI
    • AI Now Institute
    • Center for AI Safety
  • Business AI
    • Advanced AI News Features
    • Finance AI
    • Healthcare AI
    • Education AI
    • Energy AI
    • Legal AI
LinkedIn Instagram YouTube Threads X (Twitter)
Advanced AI News
Hugging Face

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

By Advanced AI EditorJune 8, 2025No Comments2 Mins Read
Share Facebook Twitter Pinterest Copy Link Telegram LinkedIn Tumblr Email
Share
Facebook Twitter LinkedIn Pinterest Email


MINT-CoT enhances multimodal mathematical reasoning by interleaving visual tokens into textual chain-of-thought steps, enabling flexible visual perception and improved problem-solving.

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



Source link

Follow on Google News Follow on Flipboard
Share. Facebook Twitter Pinterest LinkedIn Tumblr Email Copy Link
Previous ArticleClass Dismissed? Representative Claims in Getty v. Stability AI | Cooley LLP
Next Article 16 Iconic Wild Animals Photos Celebrating Remembering Wildlife
Advanced AI Editor
  • Website

Related Posts

Paper page – Can Large Multimodal Models Actively Recognize Faulty Inputs? A Systematic Evaluation Framework of Their Input Scrutiny Ability

August 9, 2025

Paper page – Evaluating, Synthesizing, and Enhancing for Customer Support Conversation

August 9, 2025

Paper page – Hop, Skip, and Overthink: Diagnosing Why Reasoning Models Fumble during Multi-Hop Analysis

August 9, 2025
Leave A Reply

Latest Posts

Midjourney Slams Lawsuit Filed by Disney to Prevent AI Training

Smithsonian Updates Museum Display on Impeachment To Include Trump

Funder Tried to Hijack Kandinsky Art Theft Suits, Says Collector

How to Stylize Your Images with Flux Kontext in ComfyUI

Latest Posts

Creating uniquely human digital banking experiences at TD

August 12, 2025

C3 AI Stock Plunges After ‘Completely Unacceptable’ Q1 Sales – C3.ai (NYSE:AI)

August 12, 2025

Meta says its Llama AI models being used by banks, tech companies

August 12, 2025

Subscribe to News

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

Recent Posts

  • Creating uniquely human digital banking experiences at TD
  • C3 AI Stock Plunges After ‘Completely Unacceptable’ Q1 Sales – C3.ai (NYSE:AI)
  • Meta says its Llama AI models being used by banks, tech companies
  • Where Can I Buy Kratom Near Me? Mit Therapy’s Tips For Smart Purchases
  • Study warns of security risks as ‘OS agents’ gain control of computers and phones

Recent Comments

  1. ThomasWep on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10
  2. ThomasWep on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10
  3. EdwardEnror on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10
  4. ThomasWep on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10
  5. Αναφορ Binance on OM1’s PhenOM® Foundation AI Surpasses One Billion Years of Health History in Model Training

Welcome to Advanced AI News—your ultimate destination for the latest advancements, insights, and breakthroughs in artificial intelligence.

At Advanced AI News, we are passionate about keeping you informed on the cutting edge of AI technology, from groundbreaking research to emerging startups, expert insights, and real-world applications. Our mission is to deliver high-quality, up-to-date, and insightful content that empowers AI enthusiasts, professionals, and businesses to stay ahead in this fast-evolving field.

Subscribe to Updates

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

LinkedIn Instagram YouTube Threads X (Twitter)
  • Home
  • About Us
  • Advertise With Us
  • Contact Us
  • DMCA
  • Privacy Policy
  • Terms & Conditions
© 2025 advancedainews. Designed by advancedainews.

Type above and press Enter to search. Press Esc to cancel.