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.
☆287Jul 17, 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:
- [ICML 2026] ZwZ model family: SOTA fine-grained perception performace; ZoomBench: a new challenging perception benchmark☆187May 4, 2026Updated 3 months ago
- ☆581May 10, 2026Updated 3 months ago
- Official repository for the paper "Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation"☆288May 28, 2026Updated 2 months ago
- Awesome List for On-Policy Distillation☆841Jul 31, 2026Updated 3 weeks ago
- Beyond SFT-to-RL: Pre-alignment via Black-BoxOn-Policy Distillation for Multimodal RL☆99May 6, 2026Updated 3 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe☆945Updated this week
- A curated collection of papers, technical reports, frameworks, and tools for on-policy distillation (OPD) of large language models☆734Aug 15, 2026Updated last week
- A curated collection of papers and resources on On-Policy Distillation for Large Language Models.☆521Aug 12, 2026Updated last week
- Code of Self-Distilled RLVR - RLSD☆64May 19, 2026Updated 3 months ago
- This repository is the official implementation for VISD.☆23May 17, 2026Updated 3 months ago
- (CVPR 2026) Long-RVOS: A Comprehensive Benchmark for Long-term Referring Video Object Segmentation☆39Feb 28, 2026Updated 5 months ago
- ☆42Jun 17, 2026Updated 2 months ago
- ☆71Feb 27, 2026Updated 5 months ago
- [CVPR 2026] Refer-Agent: A Collaborative Multi-Agent System with Reasoning and Reflection for Referring Video Object Segmentation☆37Mar 12, 2026Updated 5 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Official codes of "Sketch-in-Latents: Eliciting Unified Reasoning in MLLMs"☆17Feb 15, 2026Updated 6 months ago
- [CVPR'26] VisPlay: Self-Evolving Vision-Language Models☆72Feb 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"☆394Jul 30, 2026Updated 3 weeks ago
- Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe☆57Jun 10, 2026Updated 2 months ago
- [ICLR'26] Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology☆93Jan 26, 2026Updated 6 months ago
- ☆18Mar 1, 2026Updated 5 months ago
- (ICML 2026) Seg-ReSearch: Segmentation with Interleaved Reasoning and External Search☆50Aug 7, 2026Updated 2 weeks ago
- A collection of the latest research and resources on Fine-Grained Multimodal Perception☆32Jun 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…☆1,503Mar 9, 2026Updated 5 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- ☆92Feb 5, 2026Updated 6 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).☆36Jul 31, 2026Updated 3 weeks ago
- EVA: Efficient Reinforcement Learning for End-to-End Video Agent☆25May 6, 2026Updated 3 months ago
- [CVPR 2026] TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs☆172Jul 21, 2026Updated last month
- [ICML 2026] Official implementation of "Open-o3 Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence"☆162May 1, 2026Updated 3 months ago
- The official code of "Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning"☆101Oct 15, 2025Updated 10 months ago
- This repository is the official implementation of "Look-Back: Implicit Visual Re-focusing in MLLM Reasoning".☆99Jul 10, 2025Updated last year
- Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks☆4,354Updated this week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- [ICML 2026] Official PyTorch implementation of paper “CoCoEdit: Content-Consistent Image Editing via Region Regularized Reinforcement Lea…☆26Jun 14, 2026Updated 2 months ago
- (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…☆17Sep 8, 2025Updated 11 months ago
- ✨✨ [ICLR 2026] Think Beyond Images☆583Sep 23, 2025Updated 11 months ago
- ☆43May 9, 2026Updated 3 months ago
- [CVPR 2026] Official codes of "Monet: Reasoning in Latent Visual Space Beyond Image and Language"☆219Mar 19, 2026Updated 5 months ago
- ☆34Feb 12, 2026Updated 6 months ago