Learning Native Reflection in Unified Models: reflection SFT and multi-round Flow-GRPO RL for BAGEL
☆33Oct 20, 2026Updated 2 weeks ago
Alternatives and similar repositories for UMM-Reflection
Users that are interested in UMM-Reflection are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [EMNLP 2026] Official implementation of V-Rubrics: Visual Faithfulness via Rubric-Based Reinforcement Learning.☆60Aug 29, 2026Updated 2 months ago
- Code of "Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space Diffusion"☆28Jun 19, 2026Updated 4 months ago
- [ACL2026 oral] Uni-MMMU : A Massive Multi-discipline Multimodal Unified Benchmark☆27Apr 13, 2026Updated 6 months ago
- ☆17Oct 20, 2026Updated 2 weeks ago
- Execution Before Memory: diagnosing memory failures in video world models.☆14Oct 19, 2026Updated 2 weeks 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.
- VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning☆40Oct 5, 2026Updated last month
- Offical Implementation of "PackLab: A Comprehensive Framework for Developing, Training, and Evaluating MLLMs in Robotic Bin Packing"☆12Sep 23, 2026Updated last month
- [NeurIPS'26] Open-source native multimodal pretraining — without catastrophic forgetting.☆15Jul 2, 2026Updated 4 months ago
- [ICML 2026] The official implementation of paper "Unified Multimodal Autoregressive Modeling with Shared Context—Visual Tokenizer is Key …☆60Jul 13, 2026Updated 3 months ago
- Official implementation of "Perceptual Flow Matching for Few-Step Generative Modeling"☆36Aug 10, 2026Updated 2 months ago
- Reconstructing Big Tech T2I/T2V captioning pipelines for production and research☆45Aug 5, 2026Updated 3 months ago
- ☆31Aug 18, 2026Updated 2 months ago
- OmniTaskonomy: When Does Visual Generation Improve Visual Understanding?☆17Oct 7, 2026Updated last month
- [ECCV 2026] UniTemp: Unlocking Video Generation in Any Temporal Order via Bidirectional Distillation☆14Jun 18, 2026Updated 4 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Official implementation of "Correction Training for Diffusion Models"☆94Oct 15, 2026Updated 3 weeks ago
- A benchmark for evaluating contextual agents on realistic multimodal personal-computer environments with profiling and factual-retention …☆34Apr 2, 2026Updated 7 months ago
- FileGram: Grounding Agent Personalization in File-System Behavioral Traces☆67Oct 9, 2026Updated 3 weeks ago
- The first MoE-based framework for unified and scalable world modeling.☆25Jul 16, 2026Updated 3 months ago
- Privacy-first AI memory layer - Signal for AI Memory. E2EE, local-first, works with Claude, Cursor, and any MCP-compatible AI.☆23Jun 12, 2026Updated 4 months ago
- Official Code for GPIC: A Giant Permissive Image Corpus for Visual Generation☆62Jun 4, 2026Updated 5 months ago
- ECCV2026☆42Updated this week
- Code for Discrete Beckmann Transport Models for One-Step Language Modeling and Reasoning☆13Sep 15, 2026Updated last month
- A shared mailbox for people and their coding agents: hand results, files and context to someone else's agent (Codex, Claude Code, opencod…☆25Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- [CVPR 2026] MixFlow Training: Alleviating Exposure Bias with Slowed Interpolation Mixture☆24Dec 23, 2025Updated 10 months ago
- Demo-ICL: In-Context Learning for Procedural Video Knowledge Acquisition☆48Mar 3, 2026Updated 8 months ago
- Toolbox for GTA-Human Datasets☆25Oct 9, 2024Updated 2 years ago
- Echo: "Constantly Improving Image Models Need Constantly Improving Benchmarks" (ICLR 2026)☆20Sep 22, 2026Updated last month
- ☆27Oct 5, 2023Updated 3 years ago
- ☆25Apr 2, 2026Updated 7 months ago
- ☆14Sep 26, 2026Updated last month
- Markerless Kinematic Analysis☆20Jun 21, 2026Updated 4 months ago
- ☆14Mar 11, 2025Updated last year
- 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.
- ☆43May 9, 2026Updated 5 months ago
- OpenWorld RPG: a pixel-art open-world RPG in the browser, with the engine and editor it is built on. The world's rules are data; a langua…☆112Updated this week
- A framework that allows you to apply Sparse AutoEncoder on any models☆53Jul 11, 2025Updated last year
- DreamReasoner-8B, a large diffusion reasoning model☆20Jun 18, 2026Updated 4 months ago
- [ECCV'26] Coevolving Representations in Joint Image-Feature Diffusion☆15Sep 14, 2026Updated last month
- Official Code of SocioMind for CVPR 2024 paper "Digital Life Project: Autonomous 3D Characters with Social Intelligence"☆31Sep 9, 2024Updated 2 years ago
- Official codebase for the paper "How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance" (ICML 2026).☆19Jun 10, 2026Updated 4 months ago