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

StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets? – Takara TLDR

9 Features Of Perplexity AI Every AI User Should Try – Trak.in

Drawing Conclusions from Draws: Rethinking Preference Semantics in Arena-Style LLM Evaluation – Takara TLDR

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

RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning – Takara TLDR

By Advanced AI EditorOctober 4, 2025No Comments2 Mins Read
Share Facebook Twitter Pinterest Copy Link Telegram LinkedIn Tumblr Email
Share
Facebook Twitter LinkedIn Pinterest Email


Fine-grained visual reasoning remains a core challenge for multimodal large
language models (MLLMs). The recently introduced ReasonMap highlights this gap
by showing that even advanced MLLMs struggle with spatial reasoning in
structured and information-rich settings such as transit maps, a task of clear
practical and scientific importance. However, standard reinforcement learning
(RL) on such tasks is impeded by sparse rewards and unstable optimization. To
address this, we first construct ReasonMap-Plus, an extended dataset that
introduces dense reward signals through Visual Question Answering (VQA) tasks,
enabling effective cold-start training of fine-grained visual understanding
skills. Next, we propose RewardMap, a multi-stage RL framework designed to
improve both visual understanding and reasoning capabilities of MLLMs.
RewardMap incorporates two key designs. First, we introduce a difficulty-aware
reward design that incorporates detail rewards, directly tackling the sparse
rewards while providing richer supervision. Second, we propose a multi-stage RL
scheme that bootstraps training from simple perception to complex reasoning
tasks, offering a more effective cold-start strategy than conventional
Supervised Fine-Tuning (SFT). Experiments on ReasonMap and ReasonMap-Plus
demonstrate that each component of RewardMap contributes to consistent
performance gains, while their combination yields the best results. Moreover,
models trained with RewardMap achieve an average improvement of 3.47% across 6
benchmarks spanning spatial reasoning, fine-grained visual reasoning, and
general tasks beyond transit maps, underscoring enhanced visual understanding
and reasoning capabilities.



Source link

Follow on Google News Follow on Flipboard
Share. Facebook Twitter Pinterest LinkedIn Tumblr Email Copy Link
Previous ArticleOpenAI Enters a Special New Phase of Extreme Influence
Next Article Drawing Conclusions from Draws: Rethinking Preference Semantics in Arena-Style LLM Evaluation – Takara TLDR
Advanced AI Editor
  • Website

Related Posts

StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets? – Takara TLDR

October 4, 2025

Drawing Conclusions from Draws: Rethinking Preference Semantics in Arena-Style LLM Evaluation – Takara TLDR

October 4, 2025

ExGRPO: Learning to Reason from Experience – Takara TLDR

October 4, 2025

Comments are closed.

Latest Posts

Record Exec and Art Collector Gets Over 4 Years

New Archaeological Research Reveals Life in Pompeii Post-Eruption

Director Fired After Declining to Give Trump Sword for King Charles

Statue of Trump and Epstein Holding Hands Returns to Washington, D.C.

Latest Posts

StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets? – Takara TLDR

October 4, 2025

9 Features Of Perplexity AI Every AI User Should Try – Trak.in

October 4, 2025

Drawing Conclusions from Draws: Rethinking Preference Semantics in Arena-Style LLM Evaluation – Takara TLDR

October 4, 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

  • StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets? – Takara TLDR
  • 9 Features Of Perplexity AI Every AI User Should Try – Trak.in
  • Drawing Conclusions from Draws: Rethinking Preference Semantics in Arena-Style LLM Evaluation – Takara TLDR
  • RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning – Takara TLDR
  • OpenAI Enters a Special New Phase of Extreme Influence

Recent Comments

  1. PatrickGuide on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10
  2. Ela Braver on Down Over 40% This Year, Is C3.ai Stock Too Cheap to Pass Up?
  3. Keenan Bundrick on Meta Platforms (NasdaqGS:META) Collaborates With Booz Allen To Pioneer AI-Powered Space Tech
  4. Valda Neat on Stanford HAI’s 2025 AI Index Reveals Record Growth in AI Capabilities, Investment, and Regulation
  5. Karon Arb on VAST Data Powers Smarter, Evolving AI Agents with NVIDIA Data Flywheel

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.