Skip to content
View QuanjianSong's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report QuanjianSong

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

VA-TDM: A Unified View for Improving Few-Step Diffusion Models by Velocity Adversarial Distillation

Python 32 2 Updated Nov 4, 2026

Audio-guided facial video restoration and visual dubbing demos

Python 115 22 Updated Nov 5, 2026

Reverse-engineer any video, shot by shot: filmed, AI-generated or coded, and how to remake it. Breakdowns in the open VIDEO.md format. 逆向一切视频,逐个镜头看是拍的、AI 生成的还是代码做的,再告诉你怎么复刻;拆解结果按 VIDEO.md 格式输出。

Python 10,653 1,578 Updated Nov 18, 2026

Real-time generative rendering for interactive worlds, from any visual reference.

Python 450 31 Updated Nov 13, 2026

Official repository for MOSS-Image, a 5B-parameter base DiT model with high-quality text rendering, layout generation, and efficient fine-tuning.

Python 2,962 175 Updated Nov 8, 2026

Code for Connected Self Forcing: Beyond Local Learning in Video Autoregression.

9 Updated Oct 9, 2026

SolarRenderer: Few-Step Generative Reference Rendering

Python 400 17 Updated Oct 30, 2026

A Unified Large-Scale Benchmark for World Generation toward World Intelligence

Python 161 1 Updated Oct 15, 2026

Reverse engineer anything with agents, from app behavior down to native binaries.

TypeScript 468,089 114,430 Updated Nov 18, 2026

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 ext…

Python 172 4 Updated Oct 12, 2026

WorldPlay2: Extending Real-Time Interactive World Models in Control and Horizon

Python 172 19 Updated Oct 7, 2026

Autoregressive video generation with decoupled context-writing and denoising parameters, enabling up to 24-hour generation from 5s training windows.

Python 228 10 Updated Oct 31, 2026

高性价比人生指南: 长寿防病、急救、省钱理财、法律红线、失业与工伤、医保社保、恋爱婚育、怀孕育儿、创业与做平台合规、出国与技能。每条写明成本、收益、证据等级和原始出处,只引期刊论文与官方文件。

HTML 76,485 6,795 Updated Nov 16, 2026
Python 303 25 Updated Oct 15, 2026

[Arxiv 2026] WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory

Python 557 25 Updated Nov 6, 2026

Qwen's most powerful open-source image generation model

Python 2,248 166 Updated Oct 14, 2026

[MM 2024] DiffTV: Identity-preserved thermal-to-visible face translation via feature alignment and dual-stage conditions

Python 2 Updated Sep 17, 2026

[NeurIPS 2026] RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO

Python 151 3 Updated Oct 12, 2026

Official implementation of EVOKE: Endless Interactive World with Bounded State and Long-Horizon Supervision. A three-step, CFG-free interactive world model. SOTA on WBench.

Python 975 12 Updated Nov 10, 2026

OpenGame: Open Agentic Coding for Games

TypeScript 3,072 447 Updated Sep 3, 2026

Official Implementation for Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout

Python 75 3 Updated Sep 9, 2026

Official implementation of WorldinWorld

Python 145 3 Updated Sep 11, 2026

Programmable World Model: explicit world state, generative rendering.

213 8 Updated Oct 13, 2026

Official SeedVR2 Video Upscaler for ComfyUI

Python 3,000 255 Updated Dec 24, 2025

Ego4d dataset repository. Download the dataset, visualize, extract features & example usage of the dataset

Jupyter Notebook 664 68 Updated Jul 25, 2026

WorldReward & WorldReward-Bench

Python 32 Updated Sep 7, 2026

VideoDeltaNet-H3: Live T2VA / I2VA / FL2VA / Ref2VA-like generation based on Minimax H3.

Python 687 45 Updated Oct 5, 2026

Open data and scalable training for long-horizon video world models.

Python 926 54 Updated Nov 7, 2026

Zing-0.5: Toward Playable Worlds with Real-Time Joint Action and Text Control

Python 178 19 Updated Sep 17, 2026
Next