Data and corpora for the paper "PaperSearchQA: Learning to Search and Reason over Scientific Papers
with RLVR". The main dataset is `PaperSearchQA`.
James Burgess
jmhb
AI & ML interests
Vision-language models, evaluation, biology applications
Recent Activity
upvoted
a
paper
about 3 hours ago
Learning to Self-Verify Makes Language Models Better Reasoners
upvoted
a
paper
1 day ago
UniT: Unified Multimodal Chain-of-Thought Test-time Scaling
upvoted
a
paper
6 days ago
BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive
Retrieval