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.
☆239Jul 17, 2026Updated 2 weeks ago
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:
- [ICML 2026] ZwZ model family: SOTA fine-grained perception performace; ZoomBench: a new challenging perception benchmark☆183May 4, 2026Updated 2 months ago
- ☆533May 10, 2026Updated 2 months ago
- Official repository for the paper "Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation"☆277May 28, 2026Updated 2 months ago
- Awesome List for On-Policy Distillation☆793Updated this week
- Beyond SFT-to-RL: Pre-alignment via Black-BoxOn-Policy Distillation for Multimodal RL☆98May 6, 2026Updated 2 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.
- Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe☆878Jun 29, 2026Updated last month
- A curated collection of papers, technical reports, frameworks, and tools for on-policy distillation (OPD) of large language models☆608Updated this week
- A curated collection of papers and resources on On-Policy Distillation for Large Language Models.☆489Updated this week
- Code of Self-Distilled RLVR - RLSD☆62May 19, 2026Updated 2 months ago
- This repository is the official implementation for VISD.☆22May 17, 2026Updated 2 months ago
- (CVPR 2026) Long-RVOS: A Comprehensive Benchmark for Long-term Referring Video Object Segmentation☆37Feb 28, 2026Updated 5 months ago
- ☆42Jun 17, 2026Updated last month
- ☆72Feb 27, 2026Updated 5 months ago
- [CVPR 2026] Refer-Agent: A Collaborative Multi-Agent System with Reasoning and Reflection for Referring Video Object Segmentation☆35Mar 12, 2026Updated 4 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.
- Official codes of "Sketch-in-Latents: Eliciting Unified Reasoning in MLLMs"☆17Feb 15, 2026Updated 5 months ago
- [CVPR'26] VisPlay: Self-Evolving Vision-Language Models☆68Feb 25, 2026Updated 5 months ago
- [ECCV 2026] Official repo of "Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens"☆388Updated this week
- Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe☆53Jun 10, 2026Updated last month
- [ICLR'26] Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology☆91Jan 26, 2026Updated 6 months ago
- ☆17Mar 1, 2026Updated 5 months ago
- (ICML 2026) Seg-ReSearch: Segmentation with Interleaved Reasoning and External Search☆49May 1, 2026Updated 3 months ago
- A collection of the latest research and resources on Fine-Grained Multimodal Perception☆30Jun 4, 2026Updated 2 months ago
- Resources and paper list for "Thinking with Images for LVLMs". This repository accompanies our survey on how LVLMs can leverage visual in…☆1,500Mar 9, 2026Updated 4 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.
- ☆92Feb 5, 2026Updated 5 months ago
- Official PyTorch implementation of our ECCV2024 paper “Rethinking Few-shot Class-incremental Learning: Learning from Yourself”☆21Jan 12, 2025Updated last year
- Official code for "Breaking the Ceiling in On-Policy Distillation via Multi-Agent Debate" (arXiv:2605.01347).☆35Updated this week
- EVA: Efficient Reinforcement Learning for End-to-End Video Agent☆26May 6, 2026Updated 2 months ago
- [CVPR 2026] TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs☆164Jul 21, 2026Updated 2 weeks ago
- [ICML 2026] Official implementation of "Open-o3 Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence"☆158May 1, 2026Updated 3 months ago
- The official code of "Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning"☆102Oct 15, 2025Updated 9 months ago
- This repository is the official implementation of "Look-Back: Implicit Visual Re-focusing in MLLM Reasoning".☆100Jul 10, 2025Updated last year
- Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks☆4,321Updated this week
- 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.
- [ICML 2026] Official PyTorch implementation of paper “CoCoEdit: Content-Consistent Image Editing via Region Regularized Reinforcement Lea…☆26Jun 14, 2026Updated last month
- (ECCV2026) Official repository of paper "IRG-MotionLLM: Interleaving Motion Generation, Assessment and Refinement for Text-to-Motion Gene…☆30Jul 1, 2026Updated last month
- Code for "ConsistentChat: Building Skeleton-Guided Consistent Multi-Turn Dialogues for Large Language Models from Scratch", where dataset…☆16Sep 8, 2025Updated 10 months ago
- ✨✨ [ICLR 2026] Think Beyond Images☆585Sep 23, 2025Updated 10 months ago
- ☆43May 9, 2026Updated 2 months ago
- [CVPR 2026] Official codes of "Monet: Reasoning in Latent Visual Space Beyond Image and Language"☆216Mar 19, 2026Updated 4 months ago
- ☆35Feb 12, 2026Updated 5 months ago