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

Lucio, Lightbringer, Harvey, Jus Mundi, SpotDraft, LI UK + NY – Artificial Lawyer

SciVideoBench: Benchmarking Scientific Video Reasoning in Large Multimodal Models – Takara TLDR

Alibaba’s Qwen Team Takes Off! Lin Junyang Leads the Charge as a Major Player Joins the Embodied Intelligence Arena_known_team_models

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

TTRV: Test-Time Reinforcement Learning for Vision Language Models – Takara TLDR

By Advanced AI EditorOctober 10, 2025No Comments2 Mins Read
Share Facebook Twitter Pinterest Copy Link Telegram LinkedIn Tumblr Email
Share
Facebook Twitter LinkedIn Pinterest Email


Existing methods for extracting reward signals in Reinforcement Learning
typically rely on labeled data and dedicated training splits, a setup that
contrasts with how humans learn directly from their environment. In this work,
we propose TTRV to enhance vision language understanding by adapting the model
on the fly at inference time, without the need for any labeled data.
Concretely, we enhance the Group Relative Policy Optimization (GRPO) framework
by designing rewards based on the frequency of the base model’s output, while
inferring on each test sample multiple times. Further, we also propose to
control the diversity of the model’s output by simultaneously rewarding the
model for obtaining low entropy of the output empirical distribution. Our
approach delivers consistent gains across both object recognition and visual
question answering (VQA), with improvements of up to 52.4% and 29.8%,
respectively, and average boosts of 24.6% and 10.0% across 16
datasets.Remarkably, on image recognition, TTRV applied to InternVL 8B
surpasses GPT-4o by an average of 2.3% over 8 benchmarks, while remaining
highly competitive on VQA, demonstrating that test-time reinforcement learning
can match or exceed the strongest proprietary models. Finally, we find many
interesting properties of test-time RL for VLMs: for example, even in extremely
data-constrained scenarios, where adaptation is performed on a single randomly
chosen unlabeled test example, TTRV still yields non-trivial improvements of up
to 5.5% in recognition tasks.



Source link

Follow on Google News Follow on Flipboard
Share. Facebook Twitter Pinterest LinkedIn Tumblr Email Copy Link
Previous ArticleCustomizing text content moderation with Amazon Nova
Next Article OpenAI on OpenAI: Applying AI to Our Own Workflows
Advanced AI Editor
  • Website

Related Posts

SciVideoBench: Benchmarking Scientific Video Reasoning in Large Multimodal Models – Takara TLDR

October 10, 2025

NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints – Takara TLDR

October 10, 2025

SDQM: Synthetic Data Quality Metric for Object Detection Dataset Evaluation – Takara TLDR

October 10, 2025

Comments are closed.

Latest Posts

Frieze to Launch Abu Dhabi Fair in November 2026

Jeff Koons Returns to Gagosian with First New York Show in Seven Years

$45 M. Basquait Painting to Headline Sotheby’s Fall Sales in New York

Guggenheim’s 2026 Shows Include Carol Bove Survey, Taryn Simon Project

Latest Posts

Lucio, Lightbringer, Harvey, Jus Mundi, SpotDraft, LI UK + NY – Artificial Lawyer

October 10, 2025

SciVideoBench: Benchmarking Scientific Video Reasoning in Large Multimodal Models – Takara TLDR

October 10, 2025

Alibaba’s Qwen Team Takes Off! Lin Junyang Leads the Charge as a Major Player Joins the Embodied Intelligence Arena_known_team_models

October 10, 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

  • Lucio, Lightbringer, Harvey, Jus Mundi, SpotDraft, LI UK + NY – Artificial Lawyer
  • SciVideoBench: Benchmarking Scientific Video Reasoning in Large Multimodal Models – Takara TLDR
  • Alibaba’s Qwen Team Takes Off! Lin Junyang Leads the Charge as a Major Player Joins the Embodied Intelligence Arena_known_team_models
  • Qld lifts 12-year ban on IBM after $1.25bn payroll failure
  • MIT and Harvard Build “Invisible” Immune Cells That Obliterate Cancer

Recent Comments

  1. viagra stock on Building a foundation with AI to jumpstart your journalism
  2. ThomasFum on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10
  3. Thomasbarne on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10
  4. 39bet game on Building a foundation with AI to jumpstart your journalism
  5. sugammHib on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10

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.