Aruna S
@arunasank
Followers
272
Following
652
Media
48
Statuses
498
Curious about model cognition! EECS PhD student @MIT_CSAIL Past @medialab @hotosm @outreachy
Joined August 2021
RT @nsaphra: How can an imitative model like an LLM outperform the experts it is trained on? Our new COLM paper outlines three types of tra….
0
17
0
Such a fun task setting!.
Our EMNLP main paper presents a fun but very challenging benchmark for LLMs: to solve over 300+ Ace Attorney detective cases that are ultra-long-context and can only be solved by long chain-of-thoughts. Here're the lessons we learned:. - Brute test time scaling does not work for
0
0
3
RT @PeterHndrsn: I'm starting to get emails about PhDs for next year. I'm always looking for great people to join!. For next year, I'm look….
0
28
0
RT @priyald17: Beyond humbled to be on this year's #TIME100AI. AI can be an asset for climate & energy - but only if its development is gui….
0
17
0
RT @bjornlutjens: MIT News writes today about our new paper: a simple linear model outperforms a large-scale AI foundation model (ClimaX).….
0
4
0
RT @wendlerch: Our paper "Do Llamas work in English?" got featured in the new NDIF logit lens workbench during #NEMI2025🤯@VminVsky @cervisi….
0
1
0
RT @_AmilDravid: Had a great time at the 2025 New England Mechanistic Interpretability (NEMI) workshop. Thanks to the organizers! . If you….
0
3
0
Chandra, the biography of Subrahmanyan Chandrasekhar is a source of everlasting motivation for me to be a scientist.
Subrahmanyan Chandrasekhar, the great astrophysicist, showed humility and curiosity in his research. In 1967, at age ~57, he wrote to a 25-year-old Stephen Hawking, asking for guidance on the math behind Hawking’s work on cosmological singularities. 1/
0
0
3
RT @Pavan_KumarGV: Subrahmanyan Chandrasekhar, the great astrophysicist, showed humility and curiosity in his research. In 1967, at age ~57….
0
305
0
RT @gvrkiran: I wrote about what we know about how people in the global south (particularly India) are using AI. h….
0
5
0
RT @radamihalcea: 🐕 🐒 It was a special treat to give a keynote today on one of my favorite topics: AI for animal communication. This was my….
0
9
0
RT @davidbau: Announcing a deep net interpretability talk series!. Every week you will find new talks on recent research in the science of….
youtube.com
We're a research computing project cracking open the mysteries inside large-scale AI systems. The NSF National Deep Inference Fabric consists of a unique combination of hardware and software that...
0
23
0
RT @StephenLCasper: A personal update:.- I just finished my 6-month residency at @AISecurityInst. - I'm going back to MIT for the final yea….
0
24
0
RT @davidbau: Thanks to all for making NEMI 2025 a wonderful event. Fascinating talks, inspiring posters, important discussions. You surfa….
0
15
0
RT @aryaman2020: my good friend Atticus Geiger has written an interesting new paper on causal abstraction <=> philosophy of computation! si….
0
14
0
RT @lisabdunlap: Don't know what to get your advisor for their birthday? Give them the best gift of all: their time back. Happy (late) bi….
0
8
0
RT @sebschu: Work with me and @najoungkim on a cool project evaluating the latest agents. Joining us at BU would be preferable but if you….
0
7
0
RT @najoungkim: I'll be at NEMI most of the day! come talk to me about interp & cogsci, role of behavioral evidence vs. other kinds, compos….
0
1
0
RT @kpal_koyena: Had a great time organizing #NEMI again! Really amazing to see this field growing — we doubled in size from last year’s NE….
0
5
0