6 papers
EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generation
Ruozhen He, Meng Wei, Ziyan Yang +1
Multi-shot video generation extends single-shot generation to coherent visual narratives, yet maintaining consistent characters, objects, and locations across shots remains a chall…
NoiseShift: Resolution-Aware Noise Recalibration for Better Low-Resolution Image Generation
Ruozhen He, Moayed Haji-Ali, Ziyan Yang +1
Text-to-image diffusion models often degrade when sampled at resolutions outside the final training resolution set. Prior work has largely emphasized higher resolution generation,…
Agentic Discovery with Active Hypothesis Exploration for Visual Recognition
Jaywon Koo, Jefferson Hernandez, Ruozhen He +3
We introduce HypoExplore, an agentic framework that formulates neural architecture discovery for visual recognition as a hypothesis-driven scientific inquiry. Given a human-specifi…
Beyond Referring Expressions: Scenario Comprehension Visual Grounding
Ruozhen He, Nisarg A. Shah, Qihua Dong +3
Existing visual grounding benchmarks primarily evaluate alignment between image regions and literal referring expressions, where models can often succeed by matching a prominent na…
GViT: Representing Images as Gaussians for Visual Recognition
Jefferson Hernandez, Ruozhen He, Guha Balakrishnan +2
We introduce GVIT, a classification framework that abandons conventional pixel or patch grid input representations in favor of a compact set of learnable 2D Gaussians. Each image i…
Learning from Synthetic Data for Visual Grounding
Ruozhen He, Ziyan Yang, Paola Cascante-Bonilla +2
This paper extensively investigates the effectiveness of synthetic training data to improve the capabilities of vision-and-language models for grounding textual descriptions to ima…