REVIEW 6 cited by
ControlVAR: Exploring Controllable Visual Autoregressive Modeling
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
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}.
Forward citations
Cited by 6 Pith papers
-
Structure-Detail Decoupled Autoregressive Generation for Fast and High-Fidelity Virtual Try-On
STAR-VTON decouples latent VAR structure synthesis from pixel-space matching-based detail recovery, yielding faster high-fidelity virtual try-on than diffusion baselines.
-
Layout-Conditioned Autoregressive Text-to-Image Generation via Structured Masking
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.
-
LaVieID: Local Autoregressive Diffusion Transformers for Identity-Preserving Video Creation
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.
-
HMAR: Efficient Hierarchical Masked Auto-Regressive Image Generation
HMAR is an image generator that builds each resolution scale from the previous scale and refines it with masked prediction, matching or improving ImageNet FID/IS versus VAR with faster training and inference.
-
DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer
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.
-
CycleVAR: Repurposing Autoregressive Model for Unsupervised One-Step Image Translation
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.
Discussion (0). Sign in to comment.