6 papers
PixelMoE: Scaling Pixel-Space Diffusion with LLM-Style Mixture-of-Experts
Ruixiao Dong, Jianmin Bao, Bozhi Luan +6
Pixel-space diffusion models provide an appealing alternative to latent-space diffusion models by directly modeling raw images without relying on a learned tokenizer. However, scal…
Lyapunov Probes for Hallucination Detection in Large Foundation Models
Bozhi Luan, Gen Li, Yalan Qin +6
We address hallucination detection in Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) by framing the problem through the lens of dynamical systems stabili…
BookNet: Book Image Rectification via Cross-Page Attention Network
Shaokai Liu, Hao Feng, Bozhi Luan +3
Book image rectification presents unique challenges due to its complex geometric distortions from binding constraints, where left and right pages exhibit distinctly asymmetric curv…
Multi-Cue Adaptive Visual Token Pruning for Large Vision-Language Models
Bozhi Luan, Wengang Zhou, Hao Feng +3
As the computational needs of Large Vision-Language Models (LVLMs) increase, visual token pruning has proven effective in improving inference speed and memory efficiency. Tradition…
TextCoT: Zoom In for Enhanced Multimodal Text-Rich Image Understanding
Bozhi Luan, Hao Feng, Hong Chen +3
The advent of Large Multimodal Models (LMMs) has sparked a surge in research aimed at harnessing their remarkable reasoning abilities. However, for understanding text-rich images,…
Improving Handwritten OCR with Training Samples Generated by Glyph Conditional Denoising Diffusion Probabilistic Model
Haisong Ding, Bozhi Luan, Dongnan Gui +2
Constructing a highly accurate handwritten OCR system requires large amounts of representative training data, which is both time-consuming and expensive to collect. To mitigate the…