4 papers
Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers
Adam Karvonen, James Chua, Clément Dumas +8
Large language model (LLM) activations are notoriously difficult to understand, with most existing techniques using complex, specialized methods for interpreting them. Recent work…
Unveiling Glitches: A Deep Dive into Image Encoding Bugs within CLIP
Ayush Ranjan, Daniel Wen, Karthik Bhat
Understanding the limitations and weaknesses of state-of-the-art models in artificial intelligence is crucial for their improvement and responsible application. In this research, w…
Improving Generative Adversarial Networks for Video Super-Resolution
Daniel Wen
In this research, we explore different ways to improve generative adversarial networks for video super-resolution tasks from a base single image super-resolution GAN model. Our pri…
Directed Domain Fine-Tuning: Tailoring Separate Modalities for Specific Training Tasks
Daniel Wen, Nafisa Hussain
Large language models (LLMs) and large visual language models (LVLMs) have been at the forefront of the artificial intelligence field, particularly for tasks like text generation,…