Boqing Gong

Fine-grained Token Allocation Via Operation Pruning for Efficient MLLMs

Culture in Action: Evaluating Text-to-Image Models through Social Activities

The LLM Bottleneck: Why Open-Source Vision LLMs Struggle with Hierarchical Visual Understanding

Vision LLMs Are Bad at Hierarchical Visual Understanding, and LLMs Are the Bottleneck

The Crystal Ball Hypothesis in diffusion models: Anticipating object positions from initial noise

Epsilon-VAE: Denoising as Visual Decoding

OmnixR: Evaluating Omni-modality Language Models on Reasoning across Modalities

Automatic Jailbreaking of Text-to-Image Generative AI Systems for Copyright Infringement

$\epsilon$-VAE: Denoising as Visual Decoding

Neptune: The Long Orbit to Benchmarking Long Video Understanding

IndianRoad: A Video Dataset of Diverse Atomic Visual Elements in Dense and Unpredictable Environments