GEAR jointly trains VQ tokenizer and AR generator end-to-end via dual hard/soft read-out and representation alignment, achieving up to 10x faster ImageNet gFID convergence than LlamaGen-REPA while generalizing across quantizers and to text-to-image.
Autoregressive image generation without vector quantization.Advances in Neural Information Processing Systems, 37:56424–56445
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
method 1
citation-polarity summary
years
2026 7verdicts
UNVERDICTED 7representative citing papers
ImageAttributionBench is a benchmark dataset demonstrating that state-of-the-art image attribution methods lack robustness to image degradation and fail to generalize to semantically disjoint domains.
SemaVoice adds SFM-guided alignment to refine continuous speech representations in autoregressive TTS, reporting 1.71% English WER on Seed-TTS and competitiveness with open-source SOTA.
Projecting VAE latents to a fixed spherical radius and replacing linear interpolation with spherical linear interpolation improves class-conditional ImageNet-256 FID while leaving the diffusion architecture unchanged.
Constructs continuous sign conversation data from isolated signs using retrieval and diffusion models to train a direct sign-to-sign conversational AI.
AID-VAR attaches an adversarial discriminator and lightweight guidance injector to frozen VAR backbones to diagnose and correct fidelity gaps across scales, reporting 16% FID gains with 3% added parameters.
Using understanding tasks as direct supervision during post-training improves image generation and editing in unified multimodal models.
citing papers explorer
-
Towards Continuous Sign Language Conversation from Isolated Signs
Constructs continuous sign conversation data from isolated signs using retrieval and diffusion models to train a direct sign-to-sign conversational AI.