BiWM: Advancing Open-Source Interactive Video World Models with Bidirectional Autoregression

• URL: http://arxiv.org/abs/2606.10135v2
• Date: Wed, 10 Jun 2026 12:21:54 GMT
• Title: BiWM: Advancing Open-Source Interactive Video World Models with Bidirectional Autoregression
• Abstract summary: We present BiWM, the first full-stack framework for interactive video world models under the bidirectional autoregressive paradigm.<n>From a pretrained video backbone, BiWM injects camera control by fine-tuning, then runs a few-step Distribution Matching Distillation stage.<n>A single recipe spans Wan2.1-1.3B, Wan2.2-5B, HunyuanVideo-1.5-8B, and LTX-2.3-22B, and also supports secondary fine-tuning of existing bidirectional models.
• Score: 13.648620674803079
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Transitioning bidirectional video diffusion models into an autoregressive paradigm improves the interactivity of video world models, but existing causal pipelines need many stages (control fine-tuning, autoregressive training, causal initialization, few-step distillation) and still trail bidirectional models in quality due to error accumulation. Recent world models such as Yume-1.5 and Matrix-Game-3.0 instead adopt a bidirectional autoregressive approach, gaining fidelity and stable long-horizon rollout from self-correcting error propagation, yet open-source frameworks (e.g., minWM) support only causal models. We present BiWM, the first full-stack framework for interactive video world models under the bidirectional autoregressive paradigm, jointly optimizing generation quality and inference speed. From a pretrained video backbone, BiWM injects camera control by fine-tuning, then runs a few-step Distribution Matching Distillation (DMD) stage that turns the backbone into an action/camera-controllable world model: just two training stages instead of four in minWM, converging in a few hundred steps on 8xH200 GPUs. A single recipe spans Wan2.1-1.3B, Wan2.2-5B, HunyuanVideo-1.5-8B, and LTX-2.3-22B, and also supports secondary fine-tuning of existing bidirectional models. BiWM enables real-world camera control where minWM loses controllability, integrates pluggable history compression (FramePack-style and PackForcing-style) for long rollouts, and offers an optional NVFP4 4-bit training/inference pipeline. To counter DMD's mode-seeking degradation, we add GAN and mass-covering forward-KL objectives that preserve scene dynamics. We open-source BiWM for resource-constrained research and high-fidelity environment simulation.

Related papers

• ForgeWM: Progressive Causal Training for Few-Step Action-Conditioned Video World Models [45.42265012012433]
  We introduce ForgeWM, a framework that transforms a bidirectional action-conditioned video generator into efficient few-step world models.<n>On paired Minecraft trajectories, ForgeWM leads the evaluated systems in Imaging Quality, reference-aligned motion-profile agreement, action-sign accuracy, and mouse-control accuracy.
  arXiv  Detail & Related papers  (2026-08-14T07:13:34Z)
• Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model [88.42070387375679]
  We introduce Flex-Forcing, a unified training and inference framework that enables a video diffusion model to seamlessly operate under both bidirectional and autoregressive generation regimes.<n>Experiments on multiple video generation benchmarks demonstrate that Flex-Forcing achieves consistently better video quality, long-video stability than strong baselines with a rigid inference schedule.
  arXiv  Detail & Related papers  (2026-07-03T17:34:14Z)
• Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models [49.369312232769154]
  We introduce Causal-rCM, a leading, unified, and scalable algorithm-infrastructure open recipe for diffusion distillation and causal training.<n>We achieve state-of-the-art streaming video generation performance in both frame-wise and chunk-wise settings, using only synthetic data for training.
  arXiv  Detail & Related papers  (2026-06-24T06:58:02Z)
• minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models [51.45338589543413]
  minWM is a full-stack open-source framework for building real-time interactive video world models.<n> minWM converts existing bidirectional T2V/TI2V video foundation models into camera-controllable few-step autoregressive world models.
  arXiv  Detail & Related papers  (2026-05-28T17:27:03Z)
• Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation [50.55853275866995]
  Real-time interactive video generation requires low-latency, streaming, and controllable rollout.<n>In this paper, we study a more aggressive setting: frame-wise autoregression with only 1--2 sampling steps.<n>We propose textbfCausal Forcing++, a principled and scalable pipeline.
  arXiv  Detail & Related papers  (2026-05-14T17:46:36Z)
• Structure From Tracking: Distilling Structure-Preserving Motion for Video Generation [76.04880323498598]
  We introduce an algorithm to distill structure-preserving motion priors from an autoregressive video tracking model (SAM2) into a bidirectional video diffusion model (CogVideoX)<n>Experiments on VBench and in human studies show that SAM2VideoX delivers consistent gains.
  arXiv  Detail & Related papers  (2025-12-12T18:56:35Z)
• MinD: Learning A Dual-System World Model for Real-Time Planning and Implicit Risk Analysis [32.08769443927576]
  We propose Manipulate in Dream (MinD), a dual-system world model for real-time, risk-aware planning.<n>MinD uses two asynchronous diffusion processes: a low-frequency visual generator (LoDiff) that predicts future scenes and a high-frequency diffusion policy (HiDiff) that outputs actions.<n>Our key insight is that robotic policies do not require fully denoised frames but can rely on low-resolution latents generated in a single denoising step.<n>MinD achieves a 63% success rate on RL-Bench, 60% on real-world Franka tasks, and operates at 11.3 FPS
  arXiv  Detail & Related papers  (2025-06-23T17:59:06Z)
• From Slow Bidirectional to Fast Autoregressive Video Diffusion Models [48.35054927704544]
  Current video diffusion models achieve impressive generation quality but struggle in interactive applications due to bidirectional attention dependencies.<n>We address this limitation by adapting a pretrained bidirectional diffusion transformer to an autoregressive transformer that generates frames on-the-fly.<n>Our model achieves a total score of 84.27 on the VBench-Long benchmark, surpassing all previous video generation models.
  arXiv  Detail & Related papers  (2024-12-10T18:59:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.