Pith. sign in

REVIEW 5 cited by

ControlVAR: Exploring Controllable Visual Autoregressive Modeling

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2406.09750 v2 pith:AAK4I4VA submitted 2024-06-14 cs.CV cs.AI

Xiang Li , Kai Qiu , Hao Chen , Jason Kuen , Zhe Lin , Rita Singh , Bhiksha Raj This is my paper
classification cs.CVcs.AI
keywords conditionalcontrolvargenerationmodelingmodelsvisualautoregressivecontrollable
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Conditional visual generation has witnessed remarkable progress with the advent of diffusion models (DMs), especially in tasks like control-to-image generation. However, challenges such as expensive computational cost, high inference latency, and difficulties of integration with large language models (LLMs) have necessitated exploring alternatives to DMs. This paper introduces ControlVAR, a novel framework that explores pixel-level controls in visual autoregressive (VAR) modeling for flexible and efficient conditional generation. In contrast to traditional conditional models that learn the conditional distribution, ControlVAR jointly models the distribution of image and pixel-level conditions during training and imposes conditional controls during testing. To enhance the joint modeling, we adopt the next-scale AR prediction paradigm and unify control and image representations. A teacher-forcing guidance strategy is proposed to further facilitate controllable generation with joint modeling. Extensive experiments demonstrate the superior efficacy and flexibility of ControlVAR across various conditional generation tasks against popular conditional DMs, \eg, ControlNet and T2I-Adaptor. Code: \url{https://github.com/lxa9867/ControlVAR}.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Structure-Detail Decoupled Autoregressive Generation for Fast and High-Fidelity Virtual Try-On

    cs.CV 2026-07 conditional novelty 6.5 of 10

    STAR-VTON decouples latent VAR structure synthesis from pixel-space matching-based detail recovery, yielding faster high-fidelity virtual try-on than diffusion baselines.

  2. Layout-Conditioned Autoregressive Text-to-Image Generation via Structured Masking

    cs.CV 2025-09 conditional novelty 6.0 of 10

    SMARLI achieves strong layout control in autoregressive text-to-image generation via structured attention masks and GRPO post-training with a CLIP-based layout reward.

  3. LaVieID: Local Autoregressive Diffusion Transformers for Identity-Preserving Video Creation

    cs.CV 2025-08 conditional novelty 6.0 of 10

    LaVieID improves identity-preserving text-to-video by routing local facial parts into early DiT blocks and autoregressively refining denoised video tokens in temporal chunks.

  4. DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer

    cs.CV 2025-07 conditional novelty 5.0 of 10

    DC-AR generates 512x512 images in 12 masked autoregressive steps plus 20 diffusion refinement steps, using a 32x compressed 2D tokenizer, and reports gFID 5.49 on MJHQ-30K.

  5. CycleVAR: Repurposing Autoregressive Model for Unsupervised One-Step Image Translation

    cs.CV 2025-06 conditional novelty 5.0 of 10

    CycleVAR adapts a pretrained visual autoregressive model to unpaired image translation using softmax-relaxed quantization and source-token prefixes, achieving FID scores competitive with CycleGAN-Turbo.

Pith tools