← Back to all news
arXiv Computer Vision By Yuzhou Ji, Jiepeng Wang, Tianyu Jin, Lizhuang Ma, Haibin Huang, Chi Zhang, Xuelong Li

WithinVAE: Compact Visual Autoencoding with Self-Distilled Semantics

Read the original on arXiv Computer Vision →

WithinVAE is a compact variational visual autoencoder that learns semantic structure internally using a sequential bottleneck and self‑distillation from an exponential‑moving‑average copy of itself. It achieves a four‑fold compression ratio on ImageNet‑1K, improving reconstruction metrics such as PSNR by 1.36 dB over RPiAE while using half the latent capacity. The model also boosts linear probing performance, demonstrating that semantic gains arise from self‑distillation rather than external supervision.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv AI
Oct 9

From Pixels, Without Pre-training: Joint Generative and Self-Supervised Representation Learning in One Model

The paper introduces SCION, a single-model framework that jointly learns generative and self‑supervised representation tasks without relying on labels or pretrained encoders. SCION uses a pixel‑space encoder conditioned on a flow timestep and a shared embedding, training contrastive and flow‑matching objectives simultaneously with gradient‑norm balancing and stop‑gradient techniques. On ImageNet 256×256, SCION achieves state‑of‑the‑art FID scores (8.92 with JiT‑B and 5.89/3.47 with JiT‑L) surpassing prior class‑unconditional and pretrained‑conditioned methods.

By Vicente Balmaseda, Ching-Long Lin, Tianbao Yang
ragdiffusion
More like this →
arXiv Computer Vision
Sep 24

UVU: Improving Multimodal Understanding via Vision-Language Unified Autoregressive Paradigm

UVU is a vision-language unified autoregressive framework that integrates visual supervision directly into the pre-training stage of multimodal large language models. By using continuous visual encoding and a large-scale iterative hierarchical clustering algorithm to build a pixel-level visual codebook, UVU enables lossless representation of visual inputs and autoregressive generation of pixel-level image tokens alongside textual tokens. This approach synergizes pixel-level visual perception with semantic-level visual understanding, allowing models to internalize visual reconstruction capabilities and improve multimodal understanding performance.

By Zhehan Kan, Xinghua Jiang, Yubo Zhu, Yanlin Liu, Xiaochen Yang, Zhixiang Wei, Shifeng Liu, Qingmin Liao, Wenming Yang, Xin Li, Yinsong Liu, Deqiang Jiang, Xing Sun
llmsefficiencymultimodal
More like this →
arXiv Computer Vision
Aug 26

AffineTok: Semantic Affine Consistency for Diffusion-Friendly Visual Tokenizer

arXiv:2608.23864v1 Announce Type: new Abstract: Visual tokenizers increasingly inject semantic supervision into latent spaces to make downstream diffusion easier. Yet how these semantics should be or...

By Junqiu Yu, Pandeng Li, Yikai Wang, Jiaxing Zhao, Yujie Wei, Kaixun Jiang, Quanhao Li, Hongtao Yu, Zhihang Liu, Zhaohe Liao, Junjie Zhou, Yun Zheng, Yu Liu, Yanwei Fu
diffusionnlpbenchmarkssafety
More like this →