René's URL Explorer Experiment


Title: GitHub - Osilly/Vision-R1: [ICLR2026] This is the first paper to explore how to effectively use R1-like RL for MLLMs and introduce Vision-R1, a reasoning MLLM that leverages cold-start initialization and RL training to incentivize reasoning capability.

Open Graph Title: GitHub - Osilly/Vision-R1: [ICLR2026] This is the first paper to explore how to effectively use R1-like RL for MLLMs and introduce Vision-R1, a reasoning MLLM that leverages cold-start initialization and RL training to incentivize reasoning capability.

X Title: GitHub - Osilly/Vision-R1: [ICLR2026] This is the first paper to explore how to effectively use R1-like RL for MLLMs and introduce Vision-R1, a reasoning MLLM that leverages cold-start initialization and RL training to incentivize reasoning capability.

Description: [ICLR2026] This is the first paper to explore how to effectively use R1-like RL for MLLMs and introduce Vision-R1, a reasoning MLLM that leverages cold-start initialization and RL training to incentivize reasoning capability. - Osilly/Vision-R1

Open Graph Description: [ICLR2026] This is the first paper to explore how to effectively use R1-like RL for MLLMs and introduce Vision-R1, a reasoning MLLM that leverages cold-start initialization and RL training to ince...

X Description: [ICLR2026] This is the first paper to explore how to effectively use R1-like RL for MLLMs and introduce Vision-R1, a reasoning MLLM that leverages cold-start initialization and RL training to ince...

Opengraph URL: https://github.com/Osilly/Vision-R1

X: @github

direct link

Domain: patch-diff.githubusercontent.com

route-pattern/:user_id/:repository
route-controllerfiles
route-actiondisambiguate
fetch-noncev2:2025b882-0516-e98f-eed5-c0d1a44800bf
current-catalog-service-hashf3abb0cc802f3d7b95fc8762b94bdcb13bf39634c40c357301c4aa1d67a256fb
request-idD496:ACF5F:4CE9B5:65F233:698285DF
html-safe-nonce58f7ec88a6752b3cf385a2899539f8438571d495a91eeaabfee8cf3b8996657f
visitor-payloadeyJyZWZlcnJlciI6IiIsInJlcXVlc3RfaWQiOiJENDk2OkFDRjVGOjRDRTlCNTo2NUYyMzM6Njk4Mjg1REYiLCJ2aXNpdG9yX2lkIjoiNTIyNTcxNjEwNDMyMTEyMDk1IiwicmVnaW9uX2VkZ2UiOiJpYWQiLCJyZWdpb25fcmVuZGVyIjoiaWFkIn0=
visitor-hmacb9b5b85b2eb67228b4af1a6ac3092c113165e19ed0368972e13fe999cf6e2f42
hovercard-subject-tagrepository:926670438
github-keyboard-shortcutsrepository,copilot
google-site-verificationApib7-x98H0j5cPqHWwSMm6dNU4GmODRoqxLiDzdx9I
octolytics-urlhttps://collector.github.com/github/collect
analytics-location//
fb:app_id1401488693436528
apple-itunes-appapp-id=1477376905, app-argument=https://github.com/Osilly/Vision-R1
twitter:imagehttps://opengraph.githubassets.com/e1063c7486bccb51b0ce1fc1739de39408ec7a466d7b473b4ca56398558c0686/Osilly/Vision-R1
twitter:cardsummary_large_image
og:imagehttps://opengraph.githubassets.com/e1063c7486bccb51b0ce1fc1739de39408ec7a466d7b473b4ca56398558c0686/Osilly/Vision-R1
og:image:alt[ICLR2026] This is the first paper to explore how to effectively use R1-like RL for MLLMs and introduce Vision-R1, a reasoning MLLM that leverages cold-start initialization and RL training to ince...
og:image:width1200
og:image:height600
og:site_nameGitHub
og:typeobject
hostnamegithub.com
expected-hostnamegithub.com
None502ff2009aec8671c806fca4ec6d758f90b6b96901b01d5f0ed23cc438efdf0f
turbo-cache-controlno-preview
go-importgithub.com/Osilly/Vision-R1 git https://github.com/Osilly/Vision-R1.git
octolytics-dimension-user_id55748410
octolytics-dimension-user_loginOsilly
octolytics-dimension-repository_id926670438
octolytics-dimension-repository_nwoOsilly/Vision-R1
octolytics-dimension-repository_publictrue
octolytics-dimension-repository_is_forkfalse
octolytics-dimension-repository_network_root_id926670438
octolytics-dimension-repository_network_root_nwoOsilly/Vision-R1
turbo-body-classeslogged-out env-production page-responsive
disable-turbofalse
browser-stats-urlhttps://api.github.com/_private/browser/stats
browser-errors-urlhttps://api.github.com/_private/browser/errors
release2e7b93cf13221e895180e11ba3b1028b0b71f0ac
ui-targetfull
theme-color#1e2327
color-schemelight dark

Links:

Skip to contenthttps://patch-diff.githubusercontent.com/Osilly/Vision-R1#start-of-content
https://patch-diff.githubusercontent.com/
Sign in https://patch-diff.githubusercontent.com/login?return_to=https%3A%2F%2Fgithub.com%2FOsilly%2FVision-R1
GitHub CopilotWrite better code with AIhttps://github.com/features/copilot
GitHub SparkBuild and deploy intelligent appshttps://github.com/features/spark
GitHub ModelsManage and compare promptshttps://github.com/features/models
MCP RegistryNewIntegrate external toolshttps://github.com/mcp
ActionsAutomate any workflowhttps://github.com/features/actions
CodespacesInstant dev environmentshttps://github.com/features/codespaces
IssuesPlan and track workhttps://github.com/features/issues
Code ReviewManage code changeshttps://github.com/features/code-review
GitHub Advanced SecurityFind and fix vulnerabilitieshttps://github.com/security/advanced-security
Code securitySecure your code as you buildhttps://github.com/security/advanced-security/code-security
Secret protectionStop leaks before they starthttps://github.com/security/advanced-security/secret-protection
Why GitHubhttps://github.com/why-github
Documentationhttps://docs.github.com
Bloghttps://github.blog
Changeloghttps://github.blog/changelog
Marketplacehttps://github.com/marketplace
View all featureshttps://github.com/features
Enterpriseshttps://github.com/enterprise
Small and medium teamshttps://github.com/team
Startupshttps://github.com/enterprise/startups
Nonprofitshttps://github.com/solutions/industry/nonprofits
App Modernizationhttps://github.com/solutions/use-case/app-modernization
DevSecOpshttps://github.com/solutions/use-case/devsecops
DevOpshttps://github.com/solutions/use-case/devops
CI/CDhttps://github.com/solutions/use-case/ci-cd
View all use caseshttps://github.com/solutions/use-case
Healthcarehttps://github.com/solutions/industry/healthcare
Financial serviceshttps://github.com/solutions/industry/financial-services
Manufacturinghttps://github.com/solutions/industry/manufacturing
Governmenthttps://github.com/solutions/industry/government
View all industrieshttps://github.com/solutions/industry
View all solutionshttps://github.com/solutions
AIhttps://github.com/resources/articles?topic=ai
Software Developmenthttps://github.com/resources/articles?topic=software-development
DevOpshttps://github.com/resources/articles?topic=devops
Securityhttps://github.com/resources/articles?topic=security
View all topicshttps://github.com/resources/articles
Customer storieshttps://github.com/customer-stories
Events & webinarshttps://github.com/resources/events
Ebooks & reportshttps://github.com/resources/whitepapers
Business insightshttps://github.com/solutions/executive-insights
GitHub Skillshttps://skills.github.com
Documentationhttps://docs.github.com
Customer supporthttps://support.github.com
Community forumhttps://github.com/orgs/community/discussions
Trust centerhttps://github.com/trust-center
Partnershttps://github.com/partners
GitHub SponsorsFund open source developershttps://github.com/sponsors
Security Labhttps://securitylab.github.com
Maintainer Communityhttps://maintainers.github.com
Acceleratorhttps://github.com/accelerator
Archive Programhttps://archiveprogram.github.com
Topicshttps://github.com/topics
Trendinghttps://github.com/trending
Collectionshttps://github.com/collections
Enterprise platformAI-powered developer platformhttps://github.com/enterprise
GitHub Advanced SecurityEnterprise-grade security featureshttps://github.com/security/advanced-security
Copilot for BusinessEnterprise-grade AI featureshttps://github.com/features/copilot/copilot-business
Premium SupportEnterprise-grade 24/7 supporthttps://github.com/premium-support
Pricinghttps://github.com/pricing
Search syntax tipshttps://docs.github.com/search-github/github-code-search/understanding-github-code-search-syntax
documentationhttps://docs.github.com/search-github/github-code-search/understanding-github-code-search-syntax
Sign in https://patch-diff.githubusercontent.com/login?return_to=https%3A%2F%2Fgithub.com%2FOsilly%2FVision-R1
Sign up https://patch-diff.githubusercontent.com/signup?ref_cta=Sign+up&ref_loc=header+logged+out&ref_page=%2F%3Cuser-name%3E%2F%3Crepo-name%3E&source=header-repo&source_repo=Osilly%2FVision-R1
Reloadhttps://patch-diff.githubusercontent.com/Osilly/Vision-R1
Reloadhttps://patch-diff.githubusercontent.com/Osilly/Vision-R1
Reloadhttps://patch-diff.githubusercontent.com/Osilly/Vision-R1
Osilly https://patch-diff.githubusercontent.com/Osilly
Vision-R1https://patch-diff.githubusercontent.com/Osilly/Vision-R1
Notifications https://patch-diff.githubusercontent.com/login?return_to=%2FOsilly%2FVision-R1
Fork 20 https://patch-diff.githubusercontent.com/login?return_to=%2FOsilly%2FVision-R1
Star 758 https://patch-diff.githubusercontent.com/login?return_to=%2FOsilly%2FVision-R1
758 stars https://patch-diff.githubusercontent.com/Osilly/Vision-R1/stargazers
20 forks https://patch-diff.githubusercontent.com/Osilly/Vision-R1/forks
Branches https://patch-diff.githubusercontent.com/Osilly/Vision-R1/branches
Tags https://patch-diff.githubusercontent.com/Osilly/Vision-R1/tags
Activity https://patch-diff.githubusercontent.com/Osilly/Vision-R1/activity
Star https://patch-diff.githubusercontent.com/login?return_to=%2FOsilly%2FVision-R1
Notifications https://patch-diff.githubusercontent.com/login?return_to=%2FOsilly%2FVision-R1
Code https://patch-diff.githubusercontent.com/Osilly/Vision-R1
Issues 3 https://patch-diff.githubusercontent.com/Osilly/Vision-R1/issues
Pull requests 0 https://patch-diff.githubusercontent.com/Osilly/Vision-R1/pulls
Actions https://patch-diff.githubusercontent.com/Osilly/Vision-R1/actions
Projects 0 https://patch-diff.githubusercontent.com/Osilly/Vision-R1/projects
Security 0 https://patch-diff.githubusercontent.com/Osilly/Vision-R1/security
Insights https://patch-diff.githubusercontent.com/Osilly/Vision-R1/pulse
Code https://patch-diff.githubusercontent.com/Osilly/Vision-R1
Issues https://patch-diff.githubusercontent.com/Osilly/Vision-R1/issues
Pull requests https://patch-diff.githubusercontent.com/Osilly/Vision-R1/pulls
Actions https://patch-diff.githubusercontent.com/Osilly/Vision-R1/actions
Projects https://patch-diff.githubusercontent.com/Osilly/Vision-R1/projects
Security https://patch-diff.githubusercontent.com/Osilly/Vision-R1/security
Insights https://patch-diff.githubusercontent.com/Osilly/Vision-R1/pulse
Brancheshttps://patch-diff.githubusercontent.com/Osilly/Vision-R1/branches
Tagshttps://patch-diff.githubusercontent.com/Osilly/Vision-R1/tags
https://patch-diff.githubusercontent.com/Osilly/Vision-R1/branches
https://patch-diff.githubusercontent.com/Osilly/Vision-R1/tags
40 Commitshttps://patch-diff.githubusercontent.com/Osilly/Vision-R1/commits/main/
https://patch-diff.githubusercontent.com/Osilly/Vision-R1/commits/main/
evaluationhttps://patch-diff.githubusercontent.com/Osilly/Vision-R1/tree/main/evaluation
evaluationhttps://patch-diff.githubusercontent.com/Osilly/Vision-R1/tree/main/evaluation
figshttps://patch-diff.githubusercontent.com/Osilly/Vision-R1/tree/main/figs
figshttps://patch-diff.githubusercontent.com/Osilly/Vision-R1/tree/main/figs
scriptshttps://patch-diff.githubusercontent.com/Osilly/Vision-R1/tree/main/scripts
scriptshttps://patch-diff.githubusercontent.com/Osilly/Vision-R1/tree/main/scripts
train/cold_starthttps://patch-diff.githubusercontent.com/Osilly/Vision-R1/tree/main/train/cold_start
train/cold_starthttps://patch-diff.githubusercontent.com/Osilly/Vision-R1/tree/main/train/cold_start
.gitignorehttps://patch-diff.githubusercontent.com/Osilly/Vision-R1/blob/main/.gitignore
.gitignorehttps://patch-diff.githubusercontent.com/Osilly/Vision-R1/blob/main/.gitignore
README.mdhttps://patch-diff.githubusercontent.com/Osilly/Vision-R1/blob/main/README.md
README.mdhttps://patch-diff.githubusercontent.com/Osilly/Vision-R1/blob/main/README.md
inference.pyhttps://patch-diff.githubusercontent.com/Osilly/Vision-R1/blob/main/inference.py
inference.pyhttps://patch-diff.githubusercontent.com/Osilly/Vision-R1/blob/main/inference.py
requirements.txthttps://patch-diff.githubusercontent.com/Osilly/Vision-R1/blob/main/requirements.txt
requirements.txthttps://patch-diff.githubusercontent.com/Osilly/Vision-R1/blob/main/requirements.txt
vllm_inference.pyhttps://patch-diff.githubusercontent.com/Osilly/Vision-R1/blob/main/vllm_inference.py
vllm_inference.pyhttps://patch-diff.githubusercontent.com/Osilly/Vision-R1/blob/main/vllm_inference.py
vllm_inference_local.pyhttps://patch-diff.githubusercontent.com/Osilly/Vision-R1/blob/main/vllm_inference_local.py
vllm_inference_local.pyhttps://patch-diff.githubusercontent.com/Osilly/Vision-R1/blob/main/vllm_inference_local.py
READMEhttps://patch-diff.githubusercontent.com/Osilly/Vision-R1
https://patch-diff.githubusercontent.com/Osilly/Vision-R1#vision-r1
Cold-start Dataset (Vision-R1-cold)https://huggingface.co/datasets/Osilly/Vision-R1-cold
RL Dataset (Vision-R1-rl)https://huggingface.co/datasets/Osilly/Vision-R1-rl
Vision-R1-CI-7Bhttps://huggingface.co/Osilly/Vision-R1-CI-7B
Vision-R1-7Bhttps://huggingface.co/Osilly/Vision-R1-7B
Vision-R1-32Bhttps://huggingface.co/Osilly/Vision-R1-32B
Vision-R1-72Bhttps://huggingface.co/Osilly/Vision-R1-72B
Paperhttps://arxiv.org/abs/2503.06749
https://patch-diff.githubusercontent.com/Osilly/Vision-R1#performance
https://patch-diff.githubusercontent.com/Osilly/Vision-R1#highlight
https://patch-diff.githubusercontent.com/Osilly/Vision-R1/blob/main/figs/IRG.png
📖 arXiv Paperhttps://arxiv.org/abs/2509.06945
🌟 GitHubhttps://github.com/Osilly/Interleaving-Reasoning-Generation
https://camo.githubusercontent.com/497faf68a7b95a1faf5af946d354e612e5f652132be1d0b502dbe29f5d6a4260/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f4f73696c6c792f496e7465726c656176696e672d526561736f6e696e672d47656e65726174696f6e2e7376673f7374796c653d736f6369616c266c6162656c3d53746172
https://patch-diff.githubusercontent.com/Osilly/Vision-R1/blob/main/figs/interleaving_reasoning.png
🌟 GitHubhttps://github.com/Osilly/Awesome-Interleaving-Reasoning
https://camo.githubusercontent.com/9cbf328a1d4edd44c58f5f12146f89b9a721c085ef7238ad0488205b6dc999af/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f4f73696c6c792f417765736f6d652d496e7465726c656176696e672d526561736f6e696e672e7376673f7374796c653d736f6369616c266c6162656c3d53746172
OpenAI o3https://openai.com/index/introducing-o3-and-o4-mini/
Deep researchhttps://openai.com/index/introducing-deep-research/
Zochihttps://github.com/IntologyAI/Zochi/blob/main/Zochi_Technical_Report.pdf
BAGELhttps://arxiv.org/abs/2505.14683
https://patch-diff.githubusercontent.com/Osilly/Vision-R1#todo-and-timeline
https://patch-diff.githubusercontent.com/Osilly/Vision-R1#todo
https://patch-diff.githubusercontent.com/Osilly/Vision-R1#timeline
RL Dataset (Vision-R1-rl)https://huggingface.co/datasets/Osilly/Vision-R1-rl
Vision-R1-CI-7Bhttps://huggingface.co/Osilly/Vision-R1-CI-7B
Vision-R1-32Bhttps://huggingface.co/Osilly/Vision-R1-32B
Vision-R1-72Bhttps://huggingface.co/Osilly/Vision-R1-72B
Vision-R1-7Bhttps://huggingface.co/Osilly/Vision-R1-7B
Cold-start Dataset (Vision-R1-cold)https://huggingface.co/datasets/Osilly/Vision-R1-cold
Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Modelshttps://arxiv.org/abs/2503.06749
https://patch-diff.githubusercontent.com/Osilly/Vision-R1#our-exploration
https://patch-diff.githubusercontent.com/Osilly/Vision-R1/blob/main/figs/exploration.png
https://patch-diff.githubusercontent.com/Osilly/Vision-R1#vision-r1-reasoning-example
https://patch-diff.githubusercontent.com/Osilly/Vision-R1/blob/main/figs/reasoning_example.png
https://patch-diff.githubusercontent.com/Osilly/Vision-R1/blob/main/figs/reasoning_example1.png
https://patch-diff.githubusercontent.com/Osilly/Vision-R1#result
https://patch-diff.githubusercontent.com/Osilly/Vision-R1/blob/main/figs/result_7B.png
https://patch-diff.githubusercontent.com/Osilly/Vision-R1#pipeline
https://patch-diff.githubusercontent.com/Osilly/Vision-R1#cold-start-initialization-data-preparation
https://patch-diff.githubusercontent.com/Osilly/Vision-R1/blob/main/figs/data_pipeline.png
https://patch-diff.githubusercontent.com/Osilly/Vision-R1#rl-training
https://patch-diff.githubusercontent.com/Osilly/Vision-R1/blob/main/figs/PTST.png
https://patch-diff.githubusercontent.com/Osilly/Vision-R1#quickstart
https://patch-diff.githubusercontent.com/Osilly/Vision-R1#train
https://patch-diff.githubusercontent.com/Osilly/Vision-R1#cold-start-initialization
https://patch-diff.githubusercontent.com/Osilly/Vision-R1#data-preparation
Vision-R1-coldhttps://huggingface.co/datasets/Osilly/Vision-R1-cold
LLaVA-CoT-100khttps://huggingface.co/datasets/Xkev/LLaVA-CoT-100k
Mulberry-SFThttps://huggingface.co/datasets/HuanjinYao/Mulberry-SFT
herehttps://github.com/hiyouga/LLaMA-Factory/blob/main/data/README.md
https://patch-diff.githubusercontent.com/Osilly/Vision-R1#training
LLaMA-Factoryhttps://github.com/hiyouga/LLaMA-Factory
train/cold_start/vision_r1_full_Qwen2.5-VL-7B-Instruct_sft_epoch2_lr5e6_warm005_32GPU/train.yamlhttps://github.com/Osilly/Vision-R1/blob/main/train/cold_start/vision_r1_full_Qwen2.5-VL-7B-Instruct_sft_epoch2_lr5e6_warm005_32GPU/train.yaml
scripthttps://github.com/Osilly/Vision-R1/blob/main/train/cold_start/vision_r1_full_Qwen2.5-VL-7B-Instruct_sft_epoch2_lr5e6_warm005_32GPU/deepseed_node.sh
https://patch-diff.githubusercontent.com/Osilly/Vision-R1#rl-training-1
RL Dataset (Vision-R1-rl)https://huggingface.co/datasets/Osilly/Vision-R1-rl
geometry3khttps://huggingface.co/datasets/hiyouga/geometry3k
EasyR1https://github.com/hiyouga/EasyR1
verlhttps://github.com/volcengine/verl
https://patch-diff.githubusercontent.com/Osilly/Vision-R1#inference
https://patch-diff.githubusercontent.com/Osilly/Vision-R1#using---transformers-for-inference
DeepSeek-R1https://huggingface.co/deepseek-ai/DeepSeek-R1/blob/main/generation_config.json
https://patch-diff.githubusercontent.com/Osilly/Vision-R1#using-vllm-for-deployment-and-inference
https://patch-diff.githubusercontent.com/Osilly/Vision-R1#start-an-openai-api-service
https://patch-diff.githubusercontent.com/Osilly/Vision-R1#inference-locally
https://patch-diff.githubusercontent.com/Osilly/Vision-R1#evalution
README.mdhttps://patch-diff.githubusercontent.com/Osilly/Vision-R1/blob/main/evaluation/README.md
https://patch-diff.githubusercontent.com/Osilly/Vision-R1#star-history
https://www.star-history.com/#Osilly/Vision-R1&Date
Readme https://patch-diff.githubusercontent.com/Osilly/Vision-R1#readme-ov-file
Please reload this pagehttps://patch-diff.githubusercontent.com/Osilly/Vision-R1
Activityhttps://patch-diff.githubusercontent.com/Osilly/Vision-R1/activity
758 starshttps://patch-diff.githubusercontent.com/Osilly/Vision-R1/stargazers
8 watchinghttps://patch-diff.githubusercontent.com/Osilly/Vision-R1/watchers
20 forkshttps://patch-diff.githubusercontent.com/Osilly/Vision-R1/forks
Report repository https://patch-diff.githubusercontent.com/contact/report-content?content_url=https%3A%2F%2Fgithub.com%2FOsilly%2FVision-R1&report=Osilly+%28user%29
Releaseshttps://patch-diff.githubusercontent.com/Osilly/Vision-R1/releases
Packages 0https://patch-diff.githubusercontent.com/users/Osilly/packages?repo_name=Vision-R1
Please reload this pagehttps://patch-diff.githubusercontent.com/Osilly/Vision-R1
Contributors 3https://patch-diff.githubusercontent.com/Osilly/Vision-R1/graphs/contributors
Please reload this pagehttps://patch-diff.githubusercontent.com/Osilly/Vision-R1
Python 99.8% https://patch-diff.githubusercontent.com/Osilly/Vision-R1/search?l=python
https://github.com
Termshttps://docs.github.com/site-policy/github-terms/github-terms-of-service
Privacyhttps://docs.github.com/site-policy/privacy-policies/github-privacy-statement
Securityhttps://github.com/security
Statushttps://www.githubstatus.com/
Communityhttps://github.community/
Docshttps://docs.github.com/
Contacthttps://support.github.com?tags=dotcom-footer

Viewport: width=device-width


URLs of crawlers that visited me.