Gabriel Pereira

gabrielpere

2 4

·

AI & ML interests

NLP researcher, occasional Kaggle competitor

Recent Activity

upvoted a paper about 2 hours ago

Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics

updated a model 6 days ago

gabrielpere/ocr-freeform-study

published a model 6 days ago

gabrielpere/ocr-freeform-study

View all activity

Organizations

None yet

gabrielpere 's models 5

gabrielpere/ocr-freeform-study

33.1k • Updated 6 days ago • 18

gabrielpere/cs229-audio-visual-learning

24.8k • Updated about 1 month ago • 9

gabrielpere/robotics-vision-language-fast-2024

16.6k • Updated Aug 27 • 8

gabrielpere/test-generation

24.8k • Updated Aug 27 • 5

gabrielpere/paper_018728155_multimodal_generation