The paper investigates whether keeping non‑spatial register tokens in vision transformer decoders improves image reconstruction and generation. Using representation autoencoders with frozen register‑equipped encoders, the authors show that joint self‑attention over both patch and register tokens yields better reconstruction quality on ImageNet‑1K, with lower FID scores and higher PSNRs compared to patch‑only baselines. For generation, a multi‑head attention pooling predictor recovers register features from sampled patches, further reducing FID by nearly 10% over the patch‑only approach.
arXiv:2609.31620v1 Announce Type: new Abstract: Representation autoencoders (RAEs) reuse features from a pretrained visual encoder as reconstruction and diffusion latents, integrating strong visual r...
arXiv:2610.03698v1 Announce Type: new Abstract: Self-supervised Vision Transformers (ViTs), such as DINOv2, learn rich visual representations, but the functions of their internal tokens remain poorly...
arXiv:2610.07729v1 Announce Type: new Abstract: Visual tokens are a major source of inference cost in vision-language models, yet simple image downsampling remains a surprisingly strong compression b...
arXiv:2610.00686v1 Announce Type: new Abstract: Recent video-based world models pair the scalability of autoregressive (AR) prediction with the visual quality of diffusion models. The choice of scene...
arXiv:2609.39924v1 Announce Type: cross Abstract: Vision-language models face a fundamental scaling bottleneck: the number of visual tokens grows with both temporal duration and spatial resolution, m...
arXiv:2605.00809v3 Announce Type: replace Abstract: In this paper, we present \textbf{Gen}erative \textbf{L}anguage-\textbf{I}mage \textbf{P}re-training (GenLIP), a minimalist generative pretraining...
Vision-language models commonly project all tokens produced by a pretrained vision encoder into a large language model. However, final-layer features can discard text, local attributes, and spatial relationships, while high-resolution inputs substantially increase context length and inference latency.
arXiv:2607.09086v2 Announce Type: replace Abstract: We present Subtoken Vision Transformer (SubViT), a selective image tokenization method for fine-grained visual recognition. Standard Vision Transfo...
arXiv:2610.17412v1 Announce Type: cross Abstract: Vision Transformers incur high computational costs when processing long visual token sequences. Existing reduction methods typically rank tokens inde...
LoopVAE introduces a recurrent depth architecture that reuses a scale‑ and loop‑conditioned core across different spatial scales while keeping resolution‑changing transitions separate. The four‑block core applies 28 block operations per encoder or decoder, enabling a 29M‑parameter convolutional model to achieve 0.28 rFID and 32.54 dB PSNR on ImageNet‑256 with roughly 65% fewer parameters than comparable VAEs. Experiments with both convolutional and Transformer operators, as well as ablations on parameter sharing, demonstrate competitive image quality metrics and reveal how targeted loop interventions and truncation affect reconstruction quality and computational trade‑offs.
arXiv:2610.19419v1 Announce Type: new Abstract: MLLM-based detectors formulate vision-language grounding as autoregressive coordinate generation, yet in dense scenes, they often collapse into a box r...
The paper investigates how attention sparsity behaves in autoregressive image generation, finding a distinct diagonal sparsity pattern due to spatial locality of visual tokens. It introduces a diagonal‑aware sparse attention mechanism that skips KV entries along the diagonal within a recent window, achieving up to 3.1× higher throughput and 1.19× lower latency with less than 2% quality loss compared to dense inference.