Self Gradient Forcing (SGF) recovers the missing context-gradient path for self-generated causal memory through a bounded two-pass replay, enabling models trained with only a 5-second window to extrapolate to minute-scale videos with stronger identity, layout, and temporal stability.
☆167Oct 12, 2026Updated 3 weeks ago
Alternatives and similar repositories for Self_Gradient_Forcing
Users that are interested in Self_Gradient_Forcing are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Autoregressive video generation with decoupled context-writing and denoising parameters, enabling up to 24-hour generation from 5s traini…☆227Updated this week
- [ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactiv…☆1,026Oct 24, 2026Updated 2 weeks ago
- Official repo for paper "Echo-Infinity: Learnable Evolving Memory for Real-Time Infinite Video Generation"☆119Jun 4, 2026Updated 5 months ago
- Open data and scalable training for long-horizon video world models.☆851Oct 31, 2026Updated last week
- Real-time planning and generation of persistent, interactive 3D worlds.☆26Oct 6, 2026Updated last month
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Context-Matched Distillation: Teacher Causality for Autoregressive Video Distillation☆72Sep 17, 2026Updated last month
- [ECCV 2026 Oral] Official implementation of "OmniForcing: Unleashing Real-time Joint Audio-Visual Generation"[arXiv:2603.11647]. OmniForc…☆203Jul 23, 2026Updated 3 months ago
- Data-Forcing Distillation (DFD): restoring diversity and fidelity in few-step video generation — text-to-video (Wan2.1) & image-to-vide…☆65Aug 30, 2026Updated 2 months ago
- [ICLR 2026] Official Repo for Rolling Forcing: Autoregressive Long Video Diffusion in Real Time☆463Oct 31, 2025Updated last year
- Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models☆156Mar 24, 2026Updated 7 months ago
- Zing-0.5: Toward Playable Worlds with Real-Time Joint Action and Text Control☆178Sep 17, 2026Updated last month
- ☆63Oct 10, 2026Updated 3 weeks ago
- Official Implementation for Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout☆74Sep 9, 2026Updated last month
- Context Forcing: Consistent Autoregressive Video Generation with Long Context [ICML26]☆123Aug 4, 2026Updated 3 months ago
- 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 Minimal and Elegant Framework & Tutorial for Real-Time Interactive World Models☆870Sep 10, 2026Updated last month
- MAGI-2-preview: Scaling Video Generation Models Efficiently☆652Aug 6, 2026Updated 3 months ago
- [CVPR 2026 Highlight] Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation☆368Dec 15, 2025Updated 10 months ago
- [ECCV 2026] ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling☆188Sep 16, 2026Updated last month
- Code World Model Official Repo☆576Aug 27, 2026Updated 2 months ago
- Official code for Echo-Memory: a controlled study of memory in action-conditioned video world models (Context, Compression, Spatial, Stat…☆251Aug 16, 2026Updated 2 months ago
- Infinite-Forcing: Towards Infinite-Long Video Generation☆154Nov 13, 2025Updated 11 months ago
- ViRDM: Taming Representation Distribution Matching for Few-Step Causal Video Generation☆25Sep 27, 2026Updated last month
- Matrix-Game 3.5: Enhancing Real-Time Streaming Interactive World Models with Patch Memory☆182Sep 7, 2026Updated 2 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.
- [CVPR 2026] Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout☆106Mar 21, 2026Updated 7 months ago
- Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence☆979Sep 17, 2026Updated last month
- JoyAI-Echo-1.5: Long-Horizon Audio-Visual Generation for Persistent Stories and Interactive Worlds☆2,071Updated this week
- [CVPR 2026] Official code of the paper "Meta-CoT: Enhancing Granularity and Generalization in Image Editing"☆79May 6, 2026Updated 6 months ago
- Hy-Nomas: Towards Free-form Interactive World Generation☆515Updated this week
- AgentGarten: Code Worlds for Evolving Agents☆221Oct 9, 2026Updated 3 weeks ago
- [Tech Report] Context Scaling: Scaling Properties of Text Conditioning in Visual Generation☆190Aug 7, 2026Updated 2 months ago
- (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models☆1,454Aug 7, 2025Updated last year
- [ICML'26] Code and website for Self-Flow: Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis☆793May 23, 2026Updated 5 months ago
- 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 List of Awesome Video World Models with AR Diffusion: Covering Algorithms, Applications, and Infrastructure, Aimed at Serving a…☆718Oct 9, 2026Updated 3 weeks ago
- Official codebase for "One-Forcing: Towards Stable One-Step Autoregressive Video Generation"☆91Sep 24, 2026Updated last month
- [ICML 2026] | Scaling Interactive World Models to 1000-Frame Horizons via Pose-Free Hierarchical Memory☆202May 4, 2026Updated 6 months ago
- Official Implementation of "DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models"☆226Updated this week
- Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)☆3,563Sep 12, 2025Updated last year
- Long Video Gen / World Model / World Action Model (Embodied) Infrastructure☆2,872Updated this week
- [ECCV 2026] Official implementation of "MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokens"☆61Jun 24, 2026Updated 4 months ago