Code is the canvas. An agent harness that turns multimodal LLMs into image and video creators.
☆40Sep 29, 2026Updated last month
Alternatives and similar repositories for MaLiang-Harness
Users that are interested in MaLiang-Harness are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [Evaluation] Can Minimax-H3 Reason About the Physical World?☆32Oct 5, 2026Updated last month
- ☆78Oct 31, 2026Updated last week
- [TPAMI 2026] Enhancing MMDiT-Based Text-to-Image Models for Similar Subject Generation☆15Mar 7, 2026Updated 8 months ago
- Official implementation of Motion Forcing: A Decoupled Framework for Robust Video Generation in Motion Dynamics☆23Mar 12, 2026Updated 7 months ago
- official implementation of CoVisco: Codec-Native Vision Encoder with Native Token Compression for Efficient Unified Visual Understanding☆30Oct 9, 2026Updated 3 weeks 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.
- ☆23Aug 23, 2026Updated 2 months ago
- [MICCAI 2025 Early Accept] Holistic White-light Polyp Classification via Alignment-free Dense Distillation of Auxiliary Optical Chromoend…☆11Dec 5, 2025Updated 11 months ago
- ☆11Jun 5, 2026Updated 5 months ago
- Training Object Permanence in World Models — the codebase☆37Sep 26, 2026Updated last month
- ☆11Aug 5, 2025Updated last year
- Agentic loop image generation without diffusion or autoregressive image models. Coding agents draw in p5.js, using iterative refinement a…☆49Oct 17, 2026Updated 3 weeks ago
- [ICCV'25] Vector Contrastive Learning For Pixel-Wise Pretraining In Medical Vision☆12Oct 26, 2025Updated last year
- [ECCV26]CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation☆57Aug 7, 2026Updated 3 months ago
- GenRouter & GenCanvas☆48Sep 2, 2026Updated 2 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.
- [CVPR 2026] Official code for BulletTime: Decoupled Control of Time and Camera Pose for Video Generation☆30Jun 1, 2026Updated 5 months ago
- [ICML 2026] Official implementation for "DirectEdit: Step-Level Accurate Inversion for Flow-Based Image Editing".☆29May 5, 2026Updated 6 months ago
- MosaicMem in Rust - Hybrid Spatial Memory for Video World Models☆19Mar 26, 2026Updated 7 months ago
- Registers Matter for Pixel-Space Diffusion Transformers☆19Jul 16, 2026Updated 3 months ago
- A curated paper list for agentic visual creation☆21Oct 4, 2026Updated last month
- Official Repositories for ArmorOCR: Grounded Adversarial Visual Perception via Observation-Transferred Self-Distillation☆21Sep 23, 2026Updated last month
- Evaluation code for RBench-V. Based on https://github.com/open-compass/VLMEvalKit.☆12May 24, 2025Updated last year
- AnyBokeh: Physics-Guided Any-to-Any Bokeh Editing with Optical Fingerprint Transfer (NeurIPS, 2026)☆33Updated this week
- ☆39Apr 6, 2026Updated 7 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.
- ☆21Aug 17, 2026Updated 2 months ago
- ☆21Mar 6, 2026Updated 8 months ago
- Common code I use in multiple projects - not RP☆11May 29, 2026Updated 5 months ago
- WeVisCut is a 9B tool-using agent that turns knowledge articles and narration scripts into multi-minute videos through planning, asset re…☆84Oct 30, 2026Updated last week
- ☆14Sep 26, 2026Updated last month
- ☆22Aug 11, 2026Updated 2 months ago
- A curated collection of papers, code, and resources on agentic video generation, world modeling, and recursive self-improvement.☆57Updated this week
- Code for paper `Learning and Reasoning with Geometry: How Generation Helps Spatial Understanding`☆16Oct 29, 2026Updated last week
- WorldMemBench: A Comprehensive Benchmark for Memory of Video World Models☆21Oct 15, 2026Updated 3 weeks 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.
- MMMG: A Massive, Multidisciplinary, Multi-Tier Generation Benchmark for Text-to-Image Reasoning [NeurIPS 2025 Poster]☆26Dec 10, 2025Updated 10 months ago
- ☆92Aug 10, 2026Updated 2 months ago
- ☆55Feb 20, 2026Updated 8 months ago
- Official Implementation of LongLive-RAG: A general retrieval-augmented framework for long video generation.☆115Jun 4, 2026Updated 5 months ago
- 4Director: Controlling Video World Models with Rigid 3D Geometry☆31Oct 6, 2026Updated last month
- ☆13Jul 10, 2024Updated 2 years ago
- Evolution of Video Generative Foundations☆49Apr 7, 2026Updated 7 months ago