Vision-OPD is a regional-to-global on-policy self-distillation framework that transfers a model's own privileged crop-conditioned perception to its full-image policy, enabling fine-grained visual understanding in a single forward pass without external teachers, labels, or verifiers.
☆348Sep 27, 2026Updated last month
Alternatives and similar repositories for Vision-OPD
Users that are interested in Vision-OPD are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆31Sep 16, 2026Updated last month
- [ICML 2026] ZwZ model family: SOTA fine-grained perception performace; ZoomBench: a new challenging perception benchmark☆199Oct 29, 2026Updated 2 weeks ago
- Awesome List for On-Policy Distillation☆883Oct 18, 2026Updated 3 weeks ago
- ☆53Jul 30, 2026Updated 3 months ago
- ☆715Sep 5, 2026Updated 2 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Official implementation of OPD-Aha for fine-grained visual perception and multimodal reasoning☆15Sep 16, 2026Updated last month
- Official repository for the paper "Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation"☆300May 28, 2026Updated 5 months ago
- A curated collection of papers, technical reports, frameworks, and tools for on-policy distillation (OPD) of large language models☆914Oct 6, 2026Updated last month
- Latent On-Policy Self-Distillation☆62Sep 22, 2026Updated last month
- [TMLR] Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe☆1,068Updated this week
- Code of Self-Distilled RLVR - RLSD☆84May 19, 2026Updated 5 months ago
- Official Implementation for "CFPO: Counterfactual Policy Optimization for Multimodal Reasoning" (ICML 2026)☆16Jul 13, 2026Updated 3 months ago
- Source code of paper "RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation"☆116Sep 14, 2026Updated last month
- NeurIPS 2026: Official implementation of “VISD: Enhancing Video Reasoning via Structured Self-Distillation”.☆26Oct 1, 2026Updated last month
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Official repo for "PAPO: Perception-Aware Policy Optimization for Multimodal Reasoning"☆167Feb 4, 2026Updated 9 months ago
- [NeurIPS 2026] Beyond SFT-to-RL: Pre-alignment via Black-BoxOn-Policy Distillation for Multimodal RL☆102May 6, 2026Updated 6 months ago
- Official codebase for the paper Latent Visual Reasoning☆191Oct 22, 2025Updated last year
- Resources and paper list for "Thinking with Images for LVLMs". This repository accompanies our survey on how LVLMs can leverage visual in…☆1,519Oct 8, 2026Updated last month
- ☆22Oct 30, 2026Updated last week
- [ECCV 2026] Official repo of "Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens"☆415Jul 30, 2026Updated 3 months ago
- A curated collection of papers and resources on On-Policy Distillation for Large Language Models.☆592Oct 13, 2026Updated 3 weeks ago
- ☆44May 28, 2026Updated 5 months ago
- [CVPR2026] Official codebase for the paper "Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space"☆88May 12, 2026Updated 6 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- ☆1,288Nov 20, 2025Updated 11 months ago
- [ICML2026]Efficient Post-Training of MLLMs for Temporal Video Grounding via On-Policy Distillation☆23Jun 29, 2026Updated 4 months ago
- ZwZ-v2: RL-trained vision-language models (4B/9B/27B) that connect fine-grained visual evidence across image regions, trained with GRPO o…☆17Oct 31, 2026Updated last week
- [ECCV 2026] Visually Grounded Commonsense Reasoning Surpervison for CLIP-like Models☆13Oct 25, 2026Updated 2 weeks ago
- CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts (ECCV2026)☆17Aug 4, 2026Updated 3 months ago
- Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe☆57Jun 10, 2026Updated 5 months ago
- [ICLR 2026] Official repo for "Spotlight on Token Perception for Multimodal Reinforcement Learning"☆93Apr 3, 2026Updated 7 months ago
- [ICLR'25] Official code for the paper 'MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs'☆397Apr 20, 2025Updated last year
- [CVPR 2026] Official codes of "Monet: Reasoning in Latent Visual Space Beyond Image and Language"☆232Mar 19, 2026Updated 7 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [ICLR'26] Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology☆94Jan 26, 2026Updated 9 months ago
- ☆98Feb 5, 2026Updated 9 months ago
- Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks☆4,483Updated this week
- Official implementation of RP-OPSD for multimodal large language models☆13Aug 13, 2026Updated 2 months ago
- ☆37Feb 12, 2026Updated 9 months ago
- On Policy Distillation Build on top of Verl☆106Sep 3, 2026Updated 2 months ago
- EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL☆5,214Updated this week
Are these results useful?