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

Early leaders in the agentic AI race show agents are here to stay

Anthropic updates Claude AI, gives users control over data-sharing for the first time

xAI Sues Apple and OpenAI Over Alleged AI Competition Suppression

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

Self-Rewarding Vision-Language Model via Reasoning Decomposition – Takara TLDR

By Advanced AI EditorAugust 29, 2025No Comments2 Mins Read
Share Facebook Twitter Pinterest Copy Link Telegram LinkedIn Tumblr Email
Share
Facebook Twitter LinkedIn Pinterest Email


Vision-Language Models (VLMs) often suffer from visual hallucinations, saying
things that are not actually in the image, and language shortcuts, where they
skip the visual part and just rely on text priors. These issues arise because
most post-training methods for VLMs rely on simple verifiable answer matching
and supervise only final outputs, leaving intermediate visual reasoning without
explicit guidance. As a result, VLMs receive sparse visual signals and often
learn to prioritize language-based reasoning over visual perception. To
mitigate this, some existing methods add visual supervision using human
annotations or distilled labels from external large models. However, human
annotations are labor-intensive and costly, and because external signals cannot
adapt to the evolving policy, they cause distributional shifts that can lead to
reward hacking. In this paper, we introduce Vision-SR1, a self-rewarding method
that improves visual reasoning without relying on external visual supervisions
via reinforcement learning. Vision-SR1 decomposes VLM reasoning into two
stages: visual perception and language reasoning. The model is first prompted
to produce self-contained visual perceptions that are sufficient to answer the
question without referring back the input image. To validate this
self-containment, the same VLM model is then re-prompted to perform language
reasoning using only the generated perception as input to compute reward. This
self-reward is combined with supervision on final outputs, providing a balanced
training signal that strengthens both visual perception and language reasoning.
Our experiments demonstrate that Vision-SR1 improves visual reasoning,
mitigates visual hallucinations, and reduces reliance on language shortcuts
across diverse vision-language tasks.



Source link

Follow on Google News Follow on Flipboard
Share. Facebook Twitter Pinterest LinkedIn Tumblr Email Copy Link
Previous ArticleHow Amazon Finance built an AI assistant using Amazon Bedrock and Amazon Kendra to support analysts for data discovery and business insights
Next Article Introducing gpt-realtime in the API
Advanced AI Editor
  • Website

Related Posts

CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning – Takara TLDR

August 29, 2025

Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies – Takara TLDR

August 28, 2025

Mind the Third Eye! Benchmarking Privacy Awareness in MLLM-powered Smartphone Agents – Takara TLDR

August 28, 2025

Comments are closed.

Latest Posts

London Museum Secures Banksy’s Piranhas

Egyptian Antiquities Trafficker Sentenced to Six Months in Prison

Sotheby’s to Launch First Series of Luxury Auctions in Abu Dhabi

Nazi-Looted Painting Turns Up in Argentinean Real Estate Listing

Latest Posts

Early leaders in the agentic AI race show agents are here to stay

August 29, 2025

Anthropic updates Claude AI, gives users control over data-sharing for the first time

August 29, 2025

xAI Sues Apple and OpenAI Over Alleged AI Competition Suppression

August 29, 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

  • Early leaders in the agentic AI race show agents are here to stay
  • Anthropic updates Claude AI, gives users control over data-sharing for the first time
  • xAI Sues Apple and OpenAI Over Alleged AI Competition Suppression
  • MIT roboticists debate the future of robotics, data, and computing
  • Nous Research drops Hermes 4 AI models that outperform ChatGPT without content restrictions

Recent Comments

  1. Harrypidge on Trump’s Tech Sanctions To Empower China, Betray America
  2. Harrypidge on TEFAF New York Illuminates Art Week With Mastery Of Vivid, Radiant Color
  3. Harrypidge on Jony Ive is building a futuristic AI device and OpenAI may acquire it
  4. Harrypidge on Sam & Jony introduce io
  5. Harrypidge on Implement human-in-the-loop confirmation with Amazon Bedrock Agents

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.