Meta CLIP 1/2
Collection
Scaling CLIP data with transparent training distribution from an end-to-end pipeline.
•
11 items
•
Updated
•
20
Cheng-Yu Hsieh
cydhsieh01
AI & ML interests
None yet
Recent Activity
upvoted
a
collection
about 1 month ago
Meta CLIP 1/2
authored
a paper
11 months ago
Perception Tokens Enhance Visual Reasoning in Multimodal Language Models
updated
a model
12 months ago
vila-molmo/molmo-dense-captioner-v22-qwen2
Organizations
upvoted
a
collection
about 1 month ago
upvoted
4
papers
over 1 year ago
Coarse Correspondence Elicit 3D Spacetime Understanding in Multimodal Language Model
Paper
•
2408.00754
•
Published
•
24
Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions
Paper
•
2407.06723
•
Published
•
11
Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps
Paper
•
2407.07071
•
Published
•
12
Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization
Paper
•
2406.16008
•
Published
•
6