Pith. sign in

REVIEW 6 cited by

Playing with Transformer at 30+ FPS via Next-Frame Diffusion

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.01380 v2 pith:767WIGSQ submitted 2025-06-02 cs.CV cs.AI

Playing with Transformer at 30+ FPS via Next-Frame Diffusion

classification cs.CV cs.AI
keywords videoautoregressivediffusiongenerationsamplingframesmodelsaction
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Autoregressive video models offer distinct advantages over bidirectional diffusion models in creating interactive video content and supporting streaming applications with arbitrary duration. In this work, we present Next-Frame Diffusion (NFD), an autoregressive diffusion transformer that incorporates block-wise causal attention, enabling iterative sampling and efficient inference via parallel token generation within each frame. Nonetheless, achieving real-time video generation remains a significant challenge for such models, primarily due to the high computational cost associated with diffusion sampling and the hardware inefficiencies inherent to autoregressive generation. To address this, we introduce two innovations: (1) We extend consistency distillation to the video domain and adapt it specifically for video models, enabling efficient inference with few sampling steps; (2) To fully leverage parallel computation, motivated by the observation that adjacent frames often share the identical action input, we propose speculative sampling. In this approach, the model generates next few frames using current action input, and discard speculatively generated frames if the input action differs. Experiments on a large-scale action-conditioned video generation benchmark demonstrate that NFD beats autoregressive baselines in terms of both visual quality and sampling efficiency. We, for the first time, achieves autoregressive video generation at over 30 Frames Per Second (FPS) on an A100 GPU using a 310M model.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Efficient Video Diffusion Models: Advancements and Challenges

    cs.CV 2026-04 unverdicted novelty 7.0

    A survey that groups efficient video diffusion methods into four paradigms—step distillation, efficient attention, model compression, and cache/trajectory optimization—and outlines open challenges for practical use.

  2. Envisioning the Future, One Step at a Time

    cs.CV 2026-04 unverdicted novelty 7.0

    An autoregressive diffusion model on sparse point trajectories predicts multi-modal future scene dynamics from single images with orders-of-magnitude faster sampling than dense video simulators while matching accuracy.

  3. Rethinking Cross-Layer Information Routing in Diffusion Transformers

    cs.CV 2026-05 conditional novelty 6.0

    DAR replaces residual addition in DiTs with learnable timestep-adaptive non-incremental aggregation of sublayer outputs, improving FID by 2.11 on ImageNet 256x256 and accelerating convergence by 8.75x.

  4. Rethinking Cross-Layer Information Routing in Diffusion Transformers

    cs.CV 2026-05 unverdicted novelty 6.0

    DAR replaces residual addition in DiTs with learnable, timestep-adaptive aggregation of sublayer outputs, yielding 2.11 FID improvement on SiT-XL/2 and 8.75x faster convergence on ImageNet 256x256.

  5. Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling

    cs.CV 2025-07 unverdicted novelty 6.0

    Geometry Forcing aligns video diffusion representations with geometric foundation model features via angular cosine and scale regression objectives to improve 3D consistency in generated videos.

  6. Matrix-game 2.0: An open-source real-time and streaming interactive world model

    cs.CV 2025-08 unverdicted novelty 5.0

    Matrix-Game 2.0 introduces a scalable data pipeline, action-injection module, and few-step distillation to enable real-time streaming video generation at 25 FPS from game-engine interactions, with open-sourced weights...