A clean single-column LaTeX preprint and technical report template with elegant typography and modern front matter.

🔥 DanceOPD: On-Policy Generative Field Distillation

[ICML 2026] LUVE : Latent-Cascaded Ultra-High-Resolution Video Generation with Dual Frequency Experts

Repo for SeedVR2 (ICLR2026) & SeedVR (CVPR2025 Highlight)

Matrix-Game 3.5: Enhancing Real-Time Streaming Interactive World Models with Patch Memory

Infinite Interactive World Rollout on a Single Desktop GPU

Official implementation of "WorldKV: Efficient World Memory with World Retrieval and Compression"

Next Forcing: World Action Modeling with Multi-Chunk Prediction (MCP)

Infinite Worlds with Versatile Interactions

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

Official Repository for Sakuga-42M Dataset

Tiny AutoEncoder for Hunyuan Video (and other video models)

Data-Forcing Distillation (DFD): restoring diversity and fidelity in few-step video generation — text-to-video (Wan2.1) & image-to-video (Cosmos), built on NVIDIA FastGen.

Official implementation of "MilliVid: Adaptive Latents for Long-Range Consistency in Video Generation"

Official Pytorch Code of the Paper "FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization"

Native Multimodal Models are World Learners

Learn everything about world model

Implementation of Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players

TriAttention — Efficient long reasoning with trigonometric KV cache compression. Enables OpenClaw local deployment on memory-constrained GPUs.

DreamX-World: A General-Purpose Interactive World Model

Interactive World Model papers organized by core research challenges.

SEA-Vision: A Multilingual Benchmark for Comprehensive Document and Scene Text Understanding in Southeast Asia

[CVPR 2026 Oral] VGGT Omega

Skills for Real Engineers. Straight from my .agents directory.

Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

[CVPR 2026] WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memories (WorldExpand of HY-World 2.0)