Related papers: Delta Forcing: Trust Region Steering for Interacti…
The ultimate goal of video generation is to satisfy a fundamental trilemma: achieving high visual quality, maintaining rigorous physical consistency, and enabling precise controllability. While recent models can maintain this balance in…
Instructional video generation is an emerging task that aims to synthesize coherent demonstrations of procedural activities from textual descriptions. Such capability has broad implications for content creation, education, and human-AI…
Post-training is the decisive step for converting a pretrained video generator into a production-oriented model that is instruction-following, controllable, and robust over long temporal horizons. This report presents a systematical…
Recent advancements in video generation have substantially improved visual quality and temporal coherence, making these models increasingly appealing for applications such as autonomous driving, particularly in the context of driving…
Incorporating camera intrinsics into video generation models offers a principled way to control not only scene dynamics but also the imaging process that governs visual appearance. Prior work has primarily focused on extrinsic control, such…
The autoregressive video diffusion model has recently gained considerable research interest due to its causal modeling and iterative denoising. In this work, we identify that the multi-head self-attention in these models under-utilizes…
Reinforcement learning (RL) has been widely used in text generation to alleviate the exposure bias issue or to utilize non-parallel datasets. The reward function plays an important role in making RL training successful. However, previous…
The generation of temporally consistent, high-fidelity driving videos over extended horizons presents a fundamental challenge in autonomous driving world modeling. Existing approaches often suffer from error accumulation and feature…
Current video diffusion models achieve impressive generation quality but struggle in interactive applications due to bidirectional attention dependencies. The generation of a single frame requires the model to process the entire sequence,…
Recent joint audio-visual diffusion models achieve remarkable generation quality but suffer from high latency due to their bidirectional attention dependencies, hindering real-time applications. We propose OmniForcing, the first framework…
Deep learning models have demonstrated exceptional performance across a wide range of computer vision tasks. However, their performance often degrades significantly when faced with distribution shifts, such as domain or dataset changes.…
Unsupervised object-centric learning from videos is a promising approach towards learning compositional representations that can be applied to various downstream tasks, such as prediction and reasoning. Recently, it was shown that…
Controllable generation, which enables fine-grained control over generated outputs, has emerged as a critical focus in visual generative models. Currently, there are two primary technical approaches in visual generation: diffusion models…
Recent advancements in video generation have enabled the development of ``world models'' capable of simulating potential futures for robotics and planning. However, specifying precise goals for these models remains a challenge; text…
Video generative models pre-trained on large-scale internet datasets have achieved remarkable success, excelling at producing realistic synthetic videos. However, they often generate clips based on static prompts (e.g., text or images),…
Video editing is a critical component of content creation that transforms raw footage into coherent works aligned with specific visual and narrative objectives. Existing approaches face two major challenges: temporal inconsistencies due to…
Current frontier video diffusion models have demonstrated remarkable results at generating high-quality videos. However, they can only generate short video clips, normally around 10 seconds or 240 frames, due to computation limitations…
Autoregressive Transformer models have demonstrated impressive performance in video generation, but their sequential token-by-token decoding process poses a major bottleneck, particularly for long videos represented by tens of thousands of…
Autoregressive models have shown superior performance and efficiency in image generation, but remain constrained by high computational costs and prolonged training times in video generation. In this study, we explore methods to accelerate…
Recent advances in video generation have been dominated by diffusion and flow-matching models, which produce high-quality results but remain computationally intensive and difficult to scale. In this work, we introduce VideoAR, the first…