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.
☆185Jun 14, 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:
- ☆470May 10, 2026Updated 2 months ago
- Official repository for the paper "Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation"☆262May 28, 2026Updated last month
- Awesome List for On-Policy Distillation☆747Jun 23, 2026Updated 3 weeks ago
- Beyond SFT-to-RL: Pre-alignment via Black-BoxOn-Policy Distillation for Multimodal RL☆95May 6, 2026Updated 2 months ago
- A curated collection of papers, technical reports, frameworks, and tools for on-policy distillation (OPD) of large language models☆520Updated this week
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- A curated collection of papers and resources on On-Policy Distillation for Large Language Models.☆436Updated this week
- Code of Self-Distilled RLVR - RLSD☆56May 19, 2026Updated last month
- This repository is the official implementation for VISD.☆20May 17, 2026Updated last month
- ☆35Jun 17, 2026Updated 3 weeks ago
- Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe☆49Jun 10, 2026Updated last month
- ☆42May 9, 2026Updated 2 months ago
- A collection of the latest research and resources on Fine-Grained Multimodal Perception☆29Jun 4, 2026Updated last month
- Official code for "Breaking the Ceiling in On-Policy Distillation via Multi-Agent Debate" (arXiv:2605.01347).☆27May 7, 2026Updated 2 months ago
- TTRV: Test-Time Reinforcement Learning for Vision–Language Models (CVPR 2026)☆46Mar 8, 2026Updated 4 months ago
- 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.
- [CVPR2026] Official codebase for the paper "Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space"☆84May 12, 2026Updated 2 months ago
- PyTorch-based open-source code for paper "SOD: Step-wise On-policy Distillation for Small Language Model Agents"☆152May 22, 2026Updated last month
- HyperEyes is a parallel multimodal search agent that fuses visual grounding and retrieval into a single atomic action, enabling concurren…☆69May 23, 2026Updated last month
- Resources and paper list for "Thinking with Images for LVLMs". This repository accompanies our survey on how LVLMs can leverage visual in…☆1,489Mar 9, 2026Updated 4 months ago
- Official code for "Self-Distilled Agentic Reinforcement Learning"☆299Updated this week
- [NeurIPS 2025] More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models☆82May 31, 2025Updated last year
- Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining (ICML2026)☆38Jun 29, 2026Updated 2 weeks ago
- [ICCV 2025] Factorized Learning for Temporally Grounded Video-Language Models☆24Apr 18, 2026Updated 2 months ago
- [ACL-26 (main)] From Verbatim to Gist Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video A…☆39Apr 19, 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.
- On Policy Distillation Build on top of Verl☆90May 25, 2026Updated last month
- [CVPR2025] Code Release of F-LMM: Grounding Frozen Large Multimodal Models☆115May 29, 2025Updated last year
- SAM4SS: Tailoring SAM and SAM2 for Semantic Segmentation☆11Jul 31, 2024Updated last year
- Weighted Reverse Convolution for Feature Upsampling☆24May 24, 2026Updated last month
- Latest Advances on (RL based) Multimodal Reasoning and Generation in Multimodal LLMs☆78Jun 12, 2026Updated last month
- ☆34Apr 10, 2026Updated 3 months ago
- Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning☆28Updated this week
- [CVPR 2026] TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs☆157Apr 27, 2026Updated 2 months ago
- Codebase for paper ToolVQA: A Dataset for Multi-step Reasoning VQA with External Tools☆31Nov 3, 2025Updated 8 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆11Oct 13, 2024Updated last year
- [CVPR'26] VisPlay: Self-Evolving Vision-Language Models☆63Feb 25, 2026Updated 4 months ago
- DepthMaster: Unified Monocular Depth Estimation for Perspective and Panoramic Images☆25Jun 13, 2026Updated last month
- [ACL 2025] PruneVid: Visual Token Pruning for Efficient Video Large Language Models☆71May 15, 2025Updated last year
- (ECCV2026) Dual Distribution Estimation for Zero-shot Noisy Test-Time Adaptation with VLMs☆15Jul 2, 2026Updated last week
- [ACL 2026 Main] See the Forest for the Trees: Loosely Speculative Decoding via Visual-Semantic Guidance for Efficient Inference of Video …☆27Jul 4, 2026Updated last week
- Pytorch Implementation of Reliable Thinking with Images.☆26May 3, 2026Updated 2 months ago