438 citations · 1.5k across the 48 of their papers we have counts for
4 papers · 2 filters
Forward Compatible Training for Large-Scale Embedding Retrieval Systems
Vivek Ramanujan, Pavan Kumar Anasosalu Vasu, Ali Farhadi +2
In visual retrieval systems, updating the embedding model requires recomputing features for every piece of data. This expensive process is referred to as backfilling. Recently, the…
Robust fine-tuning of zero-shot models
Mitchell Wortsman, Gabriel Ilharco, Jong Wook Kim +8
Large pre-trained models such as CLIP or ALIGN offer consistent accuracy across a range of data distributions when performing zero-shot inference (i.e., without fine-tuning on a sp…
MERLOT: Multimodal Neural Script Knowledge Models
Rowan Zellers, Ximing Lu, Jack Hessel +5
As humans, we understand events in the visual world contextually, performing multimodal reasoning across time to make inferences about the past, present, and future. We introduce M…
Pushing it out of the Way: Interactive Visual Navigation
Kuo-Hao Zeng, Luca Weihs, Ali Farhadi +1
We have observed significant progress in visual navigation for embodied agents. A common assumption in studying visual navigation is that the environments are static; this is a lim…