12 papers
VibeToken: Scaling 1D Image Tokenizers and Autoregressive Models for Dynamic Resolution Generations
Maitreya Patel, Jingtao Li, Weiming Zhuang +2
We introduce an efficient, resolution-agnostic autoregressive (AR) image synthesis approach that generalizes to arbitrary resolutions and aspect ratios, narrowing the gap to diffus…
MentalBlackboard: Evaluating Spatial Visualization via Mathematical Transformations
Nilay Yilmaz, Maitreya Patel, Naga Sai Abhiram Kusumba +2
Spatial visualization is the mental ability to imagine, transform, and manipulate the spatial characteristics of objects and actions. This intelligence is a part of human cognition…
EraseFlow: Learning Concept Erasure Policies via GFlowNet-Driven Alignment
Abhiram Kusumba, Maitreya Patel, Kyle Min +3
Erasing harmful or proprietary concepts from powerful text to image generators is an emerging safety requirement, yet current "concept erasure" techniques either collapse image qua…
Harnessing Synthetic Preference Data for Enhancing Temporal Understanding of Video-LLMs
Sameep Vani, Shreyas Jena, Maitreya Patel +3
While Video Large Language Models (Video-LLMs) have demonstrated remarkable performance across general video understanding benchmarks-particularly in video captioning and descripti…
AcT2I: Evaluating and Improving Action Depiction in Text-to-Image Models
Vatsal Malaviya, Agneet Chatterjee, Maitreya Patel +2
Text-to-Image (T2I) models have recently achieved remarkable success in generating images from textual descriptions. However, challenges still persist in accurately rendering compl…
RefEdit: A Benchmark and Method for Improving Instruction-based Image Editing Model on Referring Expressions
Bimsara Pathiraja, Maitreya Patel, Shivam Singh +2
Despite recent advances in inversion and instruction-based image editing, existing approaches primarily excel at editing single, prominent objects but significantly struggle when a…