📢 New dataset out! We introduce HypoGen💥, a dataset of ~5.5K structured problem–hypothesis pairs (Bit–Flip–Spark + Chain‑of‑Reasoning) to advance LLM-driven scientific ideation💡. Fine‑tuned LLaMA 3.1 8B & R1‑distilled models show significant gains. Humans are still the best🥇.

And another banger from the team led by our wondrous Sharaf Zaman 🥳 . So incredibly proud of the team, we're going open, multi-modal and inviting our community so we TBD together. A big shoutout to @mjjsmith.com and @pktrpl.bsky.social for spearheading our open community efforts 🚀 .

Was great fun cooking this up with Sharaf and team! Check out all the code at github.com/UniverseTBD/... and paper at arxiv.org/abs/2504.08583