Related papers: Infinity-RoPE: Action-Controllable Infinite Video …
Autoregressive long video generation often adopts bounded-memory streaming for efficiency, typically combining local windows for short-term continuity with static early-frame sinks as long-range anchors. However, this fixed allocation keeps…
Unified video models exhibit strong capabilities in understanding and generation, yet they struggle with reason-informed visual editing even when equipped with powerful internal vision-language models (VLMs). We attribute this gap to two…
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…
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…
Camera-conditioned video generation requires positional encoding that remains reliable under changes in camera motion, lens configuration, and scene structure. However, existing attention-level camera encodings either provide ray-only…
Visual Autoregressive (VAR) models have emerged as a strong alternative to diffusion for image synthesis, yet their fixed training resolution prevents direct generation at higher resolutions. Naively transferring training-free extrapolation…
Autoregressive video generation aims at real-time, open-ended synthesis. Yet, cinematic storytelling is not merely the endless extension of a single scene; it requires progressing through evolving events, viewpoint shifts, and discrete shot…
Generating high-quality 360{\deg} panoramic videos from perspective input is one of the crucial applications for virtual reality (VR), whereby high-resolution videos are especially important for immersive experience. Existing methods are…
Achieving streaming, fine-grained control over the outputs of autoregressive video diffusion models remains challenging, making it difficult to ensure that they consistently align with user expectations. To bridge this gap, we propose…
Generating stable and controllable character motion in real-time is a key challenge in computer animation. Existing methods often fail to provide fine-grained control or suffer from motion degradation over long sequences, limiting their use…
Video generation has recently emerged as a central task in the field of generative AI. However, the substantial computational cost inherent in video synthesis makes model distillation a critical technique for efficient deployment. Despite…
Recent advances in video super-resolution have shown that convolutional neural networks combined with motion compensation are able to merge information from multiple low-resolution (LR) frames to generate high-quality images. Current…
Autoregressive video diffusion models hold promise for world simulation but are vulnerable to exposure bias arising from the train-test mismatch. While recent works address this via post-training, they typically rely on a bidirectional…
World models allow agents to simulate the consequences of actions in imagined environments for planning, control, and long-horizon decision-making. However, existing autoregressive world models struggle with visually coherent predictions…
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…
We present ART$\boldsymbol{\cdot}$V, an efficient framework for auto-regressive video generation with diffusion models. Unlike existing methods that generate entire videos in one-shot, ART$\boldsymbol{\cdot}$V generates a single frame at a…
Streaming video generation, as one fundamental component in interactive world models and neural game engines, aims to generate high-quality, low-latency, and temporally coherent long video streams. However, most existing work suffers from…
Recent Text-to-Image (T2I) models based on rectified-flow transformers (e.g., SD3, FLUX) achieve high generative fidelity but remain vulnerable to unsafe semantics, especially when triggered by multi-token interactions. Existing mitigation…
Autoregressive video diffusion models are capable of long rollouts that are stable and consistent with history, but they are unable to guide the current generation with conditioning from the future. In camera-guided video generation with a…
Existing vector quantization (VQ) based autoregressive models follow a two-stage generation paradigm that first learns a codebook to encode images as discrete codes, and then completes generation based on the learned codebook. However, they…