Weichu Xie — accepted AI-conference papers

2026

BabyVision: Visual Reasoning Beyond Language

Liang Chen, Weichu Xie, Liang Yiyan, Hongfeng He, Haozhe Zhao, Zhibo Yang +24

ICML 2026poster

While humans develop core visual skills long before acquiring language, contemporary Multimodal LLMs (MLLMs) still rely heavily on linguistic priors to compensate for their fragile visual understanding. We uncovered a crucial fact: state-of-the-art MLLMs consistently fail on basic visual tasks that …

Cited by 0 Source ↗Scholar ↗

2025

A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation

Liang Chen, Sinan Tan, Zefan Cai, Weichu Xie, Haozhe Zhao, Yichi Zhang +4

ICLR 2025poster

This work tackles the information loss bottleneck of vector-quantization (VQ) autoregressive image generation by introducing a novel model architecture called the 2-Dimensional Autoregression (DnD) Transformer. The DnD-Transformer predicts more codes for an image by introducing a new direction, **mo…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗