@arnavic

PhD student @ University of Washington CSE | Previously @ Ai2, MSFT, Columbia, UW

Joined March 2010
  • Tweets129
  • Following174
  • Followers208
20Media
Arnavi Chheda-Kothary retweeted
Ai2
@allen_aiFeb 18
We've released a Chrome extension for Asta—a faster way to go from finding a paper to asking questions about it while you read. 🧵
4
8
1
61
4,703
Arnavi Chheda-Kothary retweeted
Barack Obama
@BarackObamaFeb 9
Congratulations to the Super Bowl champion @Seahawks! This defense was special. MVP Kenneth Walker was dominant. And Sam Darnold gave us one of the best comeback stories in a long time. Enjoy the celebration.
7,628
28,084
937
634,649
67,327,186
Ever want to ask questions about a paper, including its figures & tables? 📊📈 Want smoother interactions w/papers on desktop & mobile? Try Paper+Figure QA, a new tool from @allen_ai that answers with the original figures, tables, and excerpts from papers: paperfigureqa.allen.ai
A screenshot of a user asking about examples of how a system works in a paper, and the system responding with details about the system along with a relevant figure and caption from the paper.

ALT A screenshot of a user asking about examples of how a system works in a paper, and the system responding with details about the system along with a relevant figure and caption from the paper.

1
3
1
5
1,276
more replies
Paper+Figure QA is early and still evolving, so expect some rough edges. We’d love your feedback as we improve it! Paper+Figure QA is only available for open access papers, so there may be some papers we do not currently support. In those cases, please try a different paper.
1
51
It’s been incredible for me to return to Ai2 as a student researcher on this project with @turingmusician @lucyluwang and @josephcc, getting to combine my background in accessibility and engineering to bring this prototype to life! Please feel free to reach out with feedback.
2
84
Arnavi Chheda-Kothary retweeted
Jonathan Bragg@turingmusician6 Nov 2025
Agent benchmarks don't measure true *AI* advances We built one that's hard & trustworthy 👉AstaBench tests agents w/ *standardized tools* on 2400+ scientific research problems 👉SOTA results across 22 agent *classes* 👉AgentBaselines agents suite 🆕arxiv.org/abs/2510.21652 🧵👇

AstaBench: Rigorous Benchmarking of AI Agents with a Scientific...

AI agents hold the potential to revolutionize scientific productivity by automating literature reviews, replicating experiments, analyzing data, and even proposing new directions of inquiry;...

arxiv.org
4
21
3
30
4,260
Arnavi Chheda-Kothary retweeted
Venkatesh Potluri@venkypotluri1 Sep 2025
Replying to @umsi
@umsi we developed accessibility guidelines to evaluate AI coding tools like @Replit , @julesagent and @code . Blind or visually impaired developers, #A11Y experts and accademics, please participate in our study to ensure programming remains accessible! idea11y.dev/VibeCheck/
an image of the recruitment information: We are researchers at the IDEA Lab, University of Michigan’s School of Information. WHO WE ARE LOOKING FOR: UX designers, researchers, and specialists in digital accessibility Blind or Low-Vision (BLVI) developers Screen reader users with experience using vibe coding or coding assistance tools HCI or accessibility students/researchers Note: All participants must be 18 years and older STUDY OVERVIEW 90-minute Zoom sessions. COMPENSATION $50 AMAZON GIFT CARD SIGN UP USING THE LINk in the post HAVE QUESTIONS? Reach us at idea.lab.studies@umich.edu. Note: Due to U.S. regulations and other constraints, we are unable to invite participants residing in the EU, Cuba, Iran, North Korea, or the Crimean, Donetsk, and Luhansk regions of Ukraine. By confirming your participation, you also confirm that you do not reside in any of these regions.

ALT an image of the recruitment information: We are researchers at the IDEA Lab, University of Michigan’s School of Information. WHO WE ARE LOOKING FOR: UX designers, researchers, and specialists in digital accessibility Blind or Low-Vision (BLVI) developers Screen reader users with experience using vibe coding or coding assistance tools HCI or accessibility students/researchers Note: All participants must be 18 years and older STUDY OVERVIEW 90-minute Zoom sessions. COMPENSATION $50 AMAZON GIFT CARD SIGN UP USING THE LINk in the post HAVE QUESTIONS? Reach us at [email protected]. Note: Due to U.S. regulations and other constraints, we are unable to invite participants residing in the EU, Cuba, Iran, North Korea, or the Crimean, Donetsk, and Luhansk regions of Ukraine. By confirming your participation, you also confirm that you do not reside in any of these regions.

8
1
18
2,846
While other mediums like mobile devices have spatial affordances built in, desktops continue to feel linear and homogenous when parsing content with screen readers. (3/6)
1
131
more replies
Read more about our work here — dl.acm.org/doi/10.1145/37065…. For those at CHI, I’ll be presenting on Wednesday during the Spatial Interactions session! Please come find me then or anytime this week to chat further about all things screen readers, accessibility, and AI! (5/6)
1
120
Thank you to my collaborators, and a huge huge thank you to @BrianHCI who has stuck with me and with this work through several rejection cycles. This work happened as a part of my Master’s thesis working at the CEAL lab, and I’m grateful that we saw it over the finish line! (6/6)
93
Kicking off my very first CHI today! Great to be at #CHI2025 in beautiful Yokohama, where I’ll be presenting work on incorporating spatial interactions into desktop screen readers titled: "It Brought Me Joy": Opportunities for Spatial Browsing in Desktop Screen Readers. (1/6)
A nighttime scene of a large ship and a colorful Ferris wheel in Yokohama, Japan.

ALT A nighttime scene of a large ship and a colorful Ferris wheel in Yokohama, Japan.

1
1
13
654
In this work, we built and deployed a browser extension to enable spatial input and spatial output based screen reader interactions for increased layout understanding of web pages on desktops. (2/6)
1
68
It was such a great experience to have been a part of bringing this to the Ai2 Playground! Congrats to the whole team 🎉
Ai2
@allen_ai9 Apr 2025
For years it’s been an open question — how much is a language model learning and synthesizing information, and how much is it just memorizing and reciting? Introducing OLMoTrace, a new feature in the Ai2 Playground that begins to shed some light. 🔦
9
678
Excited to be at #IUI25 in Cagliari, Italy this week to present our paper “ArtInsight: Enabling AI-Powered Artwork Engagement for Mixed Visual-Ability Families”. You can find the full paper here: dl.acm.org/doi/full/10.1145/…
A view of the city of Cagliari, showing varying levels of buildings, a cloudy sky, and the ocean.

ALT A view of the city of Cagliari, showing varying levels of buildings, a cloudy sky, and the ocean.

1
1
4
230
In this work, we present a Human-AI system designed to facilitate deeper engagement and conversations between blind or low vision (BLV) family members and their sighted children around child-created visual artwork.
1
1
87
A huge thanks to all my collaborators, and special shoutout to my wonderful advisors @wobbrockjo and @jonfroehlich.
1
69
Arnavi Chheda-Kothary retweeted
ColumbiaCompSci@ColumbiaCompSci20 Nov 2024
Brian Smith (@BrianHCI) and the CEAL Lab are looking for PhD students to develop computers that help people perceive and interact with the world. To learn more about him - cs.columbia.edu/~brian/. For info on our PhD program bit.ly/CSPhDprogram. The deadline is December 15.
6
22
1,945
Load more