Achal Dave

achal-tri's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 5 months ago

Should VLMs be Pre-trained with Image Data?

Paper • 2503.07603 • Published Mar 10 • 3

authored 4 papers over 1 year ago

Language models scale reliably with over-training and on downstream tasks

Paper • 2403.08540 • Published Mar 13, 2024 • 15

pix2gestalt: Amodal Segmentation by Synthesizing Wholes

Paper • 2401.14398 • Published Jan 25, 2024 • 10

Understanding Video Transformers via Universal Concept Discovery

Paper • 2401.10831 • Published Jan 19, 2024 • 8

Tracking Any Object Amodally

Paper • 2312.12433 • Published Dec 19, 2023 • 12