arxiv:2306.16410
William Berrios
will33am
AI & ML interests
multimodal-learning, representation learning, generative modeling, robustness.
Recent Activity
commented
a paper
10 days ago
Multimodal Autoregressive Pre-training of Large Vision Encoders
upvoted
a
paper
10 days ago
Multimodal Autoregressive Pre-training of Large Vision Encoders
New activity
12 days ago
NinaCalvi/infobench_expert_split:Question how to generate the dataset
Organizations
Papers
1
models
None public yet
datasets
7
will33am/wikitext-2-raw-v1-preprocessed-5k-PI_KFI_claude-claude-3-5-sonnet-20240620
Viewer
•
Updated
•
5k
•
37
will33am/p72-april-may-annotated-training
Viewer
•
Updated
•
2.31k
•
39
will33am/VQAv2_sample_validation
Viewer
•
Updated
•
1k
•
46
will33am/test_mechanic
Viewer
•
Updated
•
4.8k
•
37
will33am/default_test
Viewer
•
Updated
•
10
•
42
will33am/AVA
Updated
•
36
•
1
will33am/test
Viewer
•
Updated
•
1k
•
39