arXiv Computer Vision
VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Jun 9
Video Understanding by Design: How Datasets Shape Video Models
arXiv:2509. 09151v2 Announce Type: replace-cross Abstract: Research in video understanding has advanced rapidly, driven by increasingly diverse datasets and more powerful model architectures.
arXiv AI
Jul 1
Learning Video Dynamics with Predictive Differentiable Rendering
arXiv:2606. 31050v1 Announce Type: cross Abstract: How to accurately predict a high-fidelity future world?
arXiv Computer Vision
Aug 27
4DStreamCtrl: Interactive Video Generation with Online 4D Control
The paper introduces 4DStreamCtrl, a system that unifies camera motion, object trajectories, and depth into a single 3D point‑track representation, enabling joint control, depth editing, and motion transfer in a single forward pass. By mining in‑the‑wild video for 3D motion supervision and encoding it with a lightweight Geometric Motion Head, the authors train a causal streaming student that can generate arbitrarily long videos in just four denoising steps, achieving 20 FPS on a single high‑end GPU for 480p video. This approach outperforms prior camera‑only, 2D, and offline‑3D methods in motion‑control precision while maintaining temporal coherence over hundreds of frames, thereby enabling interactive 4D‑controllable streaming generation for the first time.
arXiv Computer Vision
Sep 3
SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models
SolarWM is an open foundation for building interactive video world models, offering a reconfigurable multi‑source data engine that unifies 1.43 million clips from 10 datasets into a consistent, frame‑aligned format. It provides a backbone‑native adaptation framework that preserves native representations of models ranging from 5 B to 33 B parameters, and a three‑stage training recipe combining bidirectional adaptation, teacher‑forced autoregressive initialization, and distribution‑matching distillation. The resulting causal models can interact in real‑time over rollouts from minutes to hours, trained only on 5‑second sequences, and the project releases data, pipeline, recipes, weights, and framework for reproducible research.
arXiv AI
Jul 22
AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report
arXiv:2607. 18367v1 Announce Type: new Abstract: Unlike conventional video game development, which relies on labor-intensive pipelines for asset production, animation, physics, and programming, video world models generate interactive environments from user inputs instantly.
arXiv Computer Vision
2d ago
Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars
Avatar‑Forever introduces a decoupled parallel training framework that separates efficient generation from long‑horizon robustness, allowing each capability to be trained independently. The method employs full‑parameter distillation for high‑quality generation and a lightweight long‑horizon adapter trained via Recovery‑oriented Rollout Training (RRT) to mitigate autoregressive errors. Additionally, a ForeverCache feature‑caching mechanism reduces redundant computation during streaming inference, enabling real‑time, high‑resolution avatar generation at 27.2 FPS on a single H100 GPU.