4 papers
Xray-Visual Models: Scaling Vision models on Industry Scale Data
Shlok Mishra, Tsung-Yu Lin, Linda Wang +24
We present Xray-Visual, a unified vision model architecture for large-scale image and video understanding trained on industry-scale social media data. Our model leverages over 15 b…
An Attribute-Based Measure of Video Complexity
Aditya Sarkar, Yi Li, Zihao Wang +6
A new framework for the estimation of the complexity posed by video-question pairs to video-LLMs, Video Attribute-Based Complexity (VideoABC), is proposed. Video complexity is defi…
Identifying and Evaluating Inactive Heads in Pretrained LLMs
Pedro Sandoval-Segura, Xijun Wang, Ashwinee Panda +4
Attention is foundational to large language models (LLMs), enabling different heads to have diverse focus on relevant input tokens. However, learned behaviors like attention sinks,…
Rethinking Score Distillation as a Bridge Between Image Distributions
David McAllister, Songwei Ge, Jia-Bin Huang +4
Score distillation sampling (SDS) has proven to be an important tool, enabling the use of large-scale diffusion priors for tasks operating in data-poor domains. Unfortunately, SDS…