arxiv:2610.01092
Patrick Amadeus Irawan
patrickamadeus
AI & ML interests
NLP, Multimodality
Recent Activity
upvoted a paper 2 days ago
PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation authored a paper 4 days ago
Ego2Act: Evaluating Goal-Directed Manipulation in Egocentric Video Generation authored a paper 4 days ago
Anthropogenic Regional Adaptation in Multimodal Vision-Language ModelOrganizations
models 0
None public yet
datasets 17
patrickamadeus/the_cauldron
Viewer • Updated • 3.35M • 67
patrickamadeus/the_cauldron_shuffled
Updated • 6
patrickamadeus/coco_caption_sample
Viewer • Updated • 5k • 16
patrickamadeus/vlms-are-confused-tourists
Viewer • Updated • 5.45k • 79 • 3
patrickamadeus/coco_caption_val_unique
Viewer • Updated • 5k • 13
patrickamadeus/coco_caption_sample_mmr3
Viewer • Updated • 5k • 12
patrickamadeus/coco_caption_small_mmr3_sample
Viewer • Updated • 5k • 5
patrickamadeus/cuisines-confused-tourists
Viewer • Updated • 3.46k • 13
patrickamadeus/food-kb-compact
Viewer • Updated • 181 • 17
patrickamadeus/pawsx_mt_triplet
Updated • 203