5 papers
ExPLoRA: Parameter-Efficient Extended Pre-Training to Adapt Vision Transformers under Domain Shifts
Samar Khanna, Medhanie Irgau, David B. Lobell +1
Parameter-efficient fine-tuning (PEFT) techniques such as low-rank adaptation (LoRA) can effectively adapt large pre-trained foundation models to downstream tasks using only a smal…
Squeezed Diffusion Models
Jyotirmai Singh, Samar Khanna, James Burgess
Diffusion models typically inject isotropic Gaussian noise, disregarding structure in the data. Motivated by the way quantum squeezed states redistribute uncertainty according to t…
Mercury: Ultra-Fast Language Models Based on Diffusion
Inception Labs, Samar Khanna, Siddhant Kharbanda +10
We present Mercury, a new generation of commercial-scale large language models (LLMs) based on diffusion. These models are parameterized via the Transformer architecture and traine…
TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data
Jeremy Andrew Irvin, Emily Ruoyu Liu, Joyce Chuyi Chen +5
Large vision and language assistants have enabled new capabilities for interpreting natural images. These approaches have recently been adapted to earth observation data, but they…
Large Language Models are Geographically Biased
Rohin Manvi, Samar Khanna, Marshall Burke +2
Large Language Models (LLMs) inherently carry the biases contained in their training corpora, which can lead to the perpetuation of societal harm. As the impact of these foundation…