14 papers
Vista4D: Video Reshooting with 4D Point Clouds
Kuan Heng Lin, Zhizheng Liu, Pablo Salamanca +9
We present Vista4D, a robust and flexible video reshooting framework that grounds the input video and target cameras in a 4D point cloud. Specifically, given an input video, our me…
Multi-Token Prediction via Self-Distillation
John Kirchenbauer, Abhimanyu Hans, Brian Bartoldson +3
Existing techniques for accelerating language model inference, such as speculative decoding, require training auxiliary speculator models and building and deploying complex inferen…
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,…
Far from the Shallow: Brain-Predictive Reasoning Embedding through Residual Disentanglement
Linyang He, Tianjun Zhong, Richard Antonello +3
Understanding how the human brain progresses from processing simple linguistic inputs to performing high-level reasoning is a fundamental challenge in neuroscience. While modern la…
Small Batch Size Training for Language Models: When Vanilla SGD Works, and Why Gradient Accumulation Is Wasteful
Martin Marek, Sanae Lotfi, Aditya Somasundaram +2
Conventional wisdom dictates that small batch sizes make language model pretraining and fine-tuning unstable, motivating gradient accumulation, which trades off the number of optim…
FineGRAIN: Evaluating Failure Modes of Text-to-Image Models with Vision Language Model Judges
Kevin David Hayes, Micah Goldblum, Vikash Sehwag +3
Text-to-image (T2I) models are capable of generating visually impressive images, yet they often fail to accurately capture specific attributes in user prompts, such as the correct…