4 papers
Images are Worth Variable Length of Representations
Lingjun Mao, Rodolfo Corona, Xin Liang +2
Most existing vision encoders map images into a fixed-length sequence of tokens, overlooking the fact that different images contain varying amounts of information. For example, a v…
TULIP: Towards Unified Language-Image Pretraining
Zineng Tang, Long Lian, Seun Eisape +6
Despite the recent success of image-text contrastive models like CLIP and SigLIP, these models often struggle with vision-centric tasks that demand high-fidelity image understandin…
Evaluating Model Perception of Color Illusions in Photorealistic Scenes
Lingjun Mao, Zineng Tang, Alane Suhr
We study the perception of color illusions by vision-language models. Color illusion, where a person's visual system perceives color differently from actual color, is well-studied…
Grounding Language in Multi-Perspective Referential Communication
Zineng Tang, Lingjun Mao, Alane Suhr
We introduce a task and dataset for referring expression generation and comprehension in multi-agent embodied environments. In this task, two agents in a shared scene must take int…