Manya Wadhwa

@manyawadhwa.bsky.social did:plc:7ec4ajkv5qbpdgy22pvm46wm

PhD at UTCS | #NLP https://manyawadhwa.github.io/

No Bluesky desde 16 novembro 2023

Resumo

Manya Wadhwa (@manyawadhwa.bsky.social) é um usuário do Bluesky desde 16 novembro 2023. Tem 203 seguidores, segue 175 contas e publicou 24 posts.

Os melhores dias em que posts desta conta entraram na lista diária do Debya.

Esta conta ainda não apareceu em um ranking diário.

Curtidas públicas da rede Bluesky.

Ai2@ai2.bsky.social15/03/2026 21:01
🔎 Deep research agents like Asta ScholarQA are transforming how we perform literature review. But how do we know if the way we evaluate them is actually meaningful? Announcing our new paper: “Deep Research, Shallow Evaluation: A Case Study in Meta-Evaluation for Long-Form QA Benchmarks” 🧵
Ver post
Juan Diego Rodriguez@juand-r.bsky.social14/03/2026 05:13
I’m looking forward to reading this!
Ver post
Greg Durrett@gregdnlp.bsky.social14/03/2026 05:13
Check out Manya's benchmark for LLM creativity! Inspired by work on creativity in graphs (@adtraghunathan.bsky.social 's "roll the dice" paper), CREATE isolates testing of creative insights for discovery. Future: understanding how LLMs derive insights & how they can be better creative partners!
Ver post
Jesse Raab@jraab.bsky.social14/03/2026 05:12
Neat to see frameworks for evaluating this kind of stuff
Ver post
Jessy Li@jessyjli.bsky.social14/03/2026 05:12
Want to know how well the models can brainstorm connections across different concepts? Super excited about @manyawadhwa.bsky.social’s work on measuring associative creativity!
Ver post

No Bluesky, bloqueios são registros públicos.

Esta conta não bloqueia ninguém.