AI Papers for 04/15/2024: Modernizing Segmentation, Analyzing CLIP, and Probing 3D Awareness in Vision Models
Apr 15, 2024•11 min•Ep. 5
Episode description
AI Papers Podcast for 04/15/2024
- COCONut: Modernizing COCO Segmentation
- Scaling (Down) CLIP: A Comprehensive Analysis of Data, Architecture, and Training Strategies
- On the Robustness of Language Guidance for Low-Level Vision Tasks: Findings from Depth Estimation
- Pre-training Small Base LMs with Fewer Tokens
- Probing the 3D Awareness of Visual Foundation Models
For the best experience, listen in Metacast app for iOS or Android
