Pith. sign in

REVIEW 22 cited by

NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale

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 2508.10711 v2 pith:I4LLHNSO submitted 2025-08-14 cs.CV

NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale

classification cs.CV
keywords autoregressiveimagetokensmodelscontinuousgenerationnextstep-1discrete
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Prevailing autoregressive (AR) models for text-to-image generation either rely on heavy, computationally-intensive diffusion models to process continuous image tokens, or employ vector quantization (VQ) to obtain discrete tokens with quantization loss. In this paper, we push the autoregressive paradigm forward with NextStep-1, a 14B autoregressive model paired with a 157M flow matching head, training on discrete text tokens and continuous image tokens with next-token prediction objectives. NextStep-1 achieves state-of-the-art performance for autoregressive models in text-to-image generation tasks, exhibiting strong capabilities in high-fidelity image synthesis. Furthermore, our method shows strong performance in image editing, highlighting the power and versatility of our unified approach. To facilitate open research, we will release our code and models to the community.

discussion (0)

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

Forward citations

Cited by 22 Pith papers

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

  1. Uni-Edit: Intelligent Editing Is A General Task For Unified Model Tuning

    cs.CV 2026-05 unverdicted novelty 7.0

    Uni-Edit introduces a data synthesis pipeline turning VQA data into reasoning-intensive editing instructions, enabling single-task tuning that boosts all three capabilities in models like BAGEL and Janus-Pro.

  2. Generate "Normal", Edit Poisoned: Branding Injection via Hint Embedding in Image Editing

    cs.CR 2026-05 unverdicted novelty 7.0

    Invisible hints such as logos embedded in images are re-rendered by diffusion models during text-guided editing, enabling phishing and model-poisoning attacks with average success rates of 44.4% and 32.2%.

  3. Generative Refinement Networks for Visual Synthesis

    cs.CV 2026-04 accept novelty 7.0

    Hierarchical Binary Quantization plus global refinement AR yields 0.56 rFID reconstruction and 1.81 gFID class-conditional generation on ImageNet, with competitive T2I/T2V at 2B scale.

  4. Drift-AR: Single-Step Visual Autoregressive Generation via Anti-Symmetric Drifting

    cs.CV 2026-03 unverdicted novelty 7.0

    Drift-AR achieves 3.8-5.5x speedup in AR-diffusion image models by using entropy to enable entropy-informed speculative decoding and single-step (1-NFE) anti-symmetric drifting decoding.

  5. PlanViz: Evaluating Planning-Oriented Image Generation and Editing for Computer-Use Tasks

    cs.CV 2026-02 unverdicted novelty 7.0

    PlanViz is a new benchmark with three sub-tasks and PlanScore metric to evaluate planning-oriented image generation and editing by unified multimodal models for computer-use tasks.

  6. Drift-AR: Single-Step Visual Autoregressive Generation via Anti-Symmetric Drifting

    cs.CV 2026-03 conditional novelty 6.5

    Per-position AR prediction entropy jointly drives speculative AR decoding and an anti-symmetric single-step drift decoder, yielding 3.8–5.5× faster hybrid visual generation without distillation.

  7. Editing Everything Everywhere All at Once

    cs.CV 2026-06 unverdicted novelty 6.0

    MICE modifies joint attention biases in Multimodal Diffusion Transformers to enable concurrent multi-instance edits while reducing semantic interference via user masks.

  8. ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?

    cs.CV 2026-06 unverdicted novelty 6.0

    ImageWAM shows image editing models can replace video generation in world action models, delivering better performance with 6x lower FLOPs and 4x lower latency by using edit-derived KV caches as compact context.

  9. Channel-wise Vector Quantization

    cs.CV 2026-05 unverdicted novelty 6.0

    CVQ replaces patch-wise vector quantization with channel-wise quantization of feature maps, enabling a next-channel autoregressive model that reports 100% codebook utilization and text-to-image scores of DPG 86.7 and ...

  10. DIVA: Harnessing the Representation Divergence in Unified Multimodal Models for Mutual Reinforcement

    cs.CV 2026-05 unverdicted novelty 6.0

    DIVA factorizes visual representations in unified multimodal models into shared and unique components via complementary information flows and mutual information estimation to convert representation divergence into mut...

  11. Uni-Edit: Intelligent Editing Is A General Task For Unified Model Tuning

    cs.CV 2026-05 unverdicted novelty 6.0

    Uni-Edit frames intelligent image editing as a general task for unified multimodal models and uses an automated pipeline to synthesize complex reasoning-intensive instructions from VQA data, yielding performance gains...

  12. FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation

    cs.CV 2026-05 unverdicted novelty 6.0

    FlashAR accelerates autoregressive image generation up to 22.9x by post-training a pre-trained raster-scan model with a complementary vertical head and dynamic fusion for two-way next-token prediction.

  13. FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation

    cs.CV 2026-05 unverdicted novelty 6.0

    FlashAR achieves up to 22.9x speedup in 512x512 autoregressive image generation by post-training a pre-trained model with a complementary vertical head and dynamic fusion using only 0.05% of original training data.

  14. VibeToken: Scaling 1D Image Tokenizers and Autoregressive Models for Dynamic Resolution Generations

    cs.CV 2026-04 unverdicted novelty 6.0

    VibeToken enables autoregressive image generation at arbitrary resolutions using 64 tokens for 1024x1024 images with 3.94 gFID, constant 179G FLOPs, and better efficiency than diffusion or fixed AR baselines.

  15. Generative Refinement Networks for Visual Synthesis

    cs.CV 2026-04 unverdicted novelty 6.0

    GRN uses hierarchical binary quantization and entropy-guided refinement to set new ImageNet records of 0.56 rFID for reconstruction and 1.81 gFID for class-conditional generation while releasing code and models.

  16. Uni-ViGU: Towards Unified Video Generation and Understanding via A Diffusion-Based Video Generator

    cs.CV 2026-04 unverdicted novelty 6.0

    Uni-ViGU unifies video generation and understanding by extending a diffusion video generator with unified continuous-discrete flow matching, modality-driven MoE layers, and bidirectional training stages that repurpose...

  17. MAR-GRPO: Stabilized GRPO for AR-diffusion Hybrid Image Generation

    cs.CV 2026-04 unverdicted novelty 6.0

    MAR-GRPO stabilizes GRPO for AR-diffusion hybrids via multi-trajectory expectation and uncertainty-based token selection, yielding better visual quality, stability, and spatial understanding than baselines.

  18. From Broad Exploration to Stable Synthesis: Entropy-Guided Optimization for Autoregressive Image Generation

    cs.LG 2026-03 unverdicted novelty 6.0

    EG-GRPO improves autoregressive text-to-image models by reallocating RL updates according to token entropy, excluding low-entropy tokens from reward signals while adding entropy bonuses to high-entropy ones, yielding ...

  19. LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens

    cs.CV 2026-02 unverdicted novelty 6.0

    LLaMo scales pretrained LLMs for unified motion-language tasks by encoding motion into continuous causal latents and adding a flow-matching head for real-time autoregressive generation and captioning.

  20. Exposing Blindspots: Cultural Bias Evaluation in Generative Image Models

    cs.CV 2025-10 conditional novelty 6.0

    When countries are not named, image models default to US-like modern styles, and iterative image editing erodes cultural fidelity that CLIPScore misses but human raters and a culture-aware VQA metric catch.

  21. F3-Tokenizer: Taming Audio Autoencoder Latents for Understanding and Generation

    cs.SD 2026-06 unverdicted novelty 5.0

    F3-Tokenizer adapts audio autoencoder latents with noise-regularized bottleneck (channel normalization and stochastic perturbation) and a representation encoder (RQ-MTP plus frozen-LLM supervision) to support both hig...

  22. Steering Visual Generation in Unified Multimodal Models with Understanding Supervision

    cs.CV 2026-05 unverdicted novelty 5.0

    Using understanding tasks as direct supervision during post-training improves image generation and editing in unified multimodal models.