🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

no one: literally no one: absolutely nobody: naina: rose bud thorn your freshman year ✨🥰🥀😋

me constantly forgetting to text back is a huge flaw but unfortunately there is literally nothing I can do about it! nothing at all case closed no further comments

If you eat the malai off cha don’t worry about what’s in the vaccine

why would i finish a thought when i could start a new more exciting one

One of the biggest criticisms of the field of post hoc #XAI is that each method "does its own thing", it is unclear how these methods relate to each other & which methods are effective under what conditions. Our #NeurIPS2022 paper provides (some) answers to these questions. [1/N]

anywhere is a walkable city if you have a lot on your mind

You’re not a monster, I said. But I lied. What I really wanted to say was that a monster is not such a terrible thing to be.

Finally, I am pleased to announce 🪢Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)🪢 Joint work with Usha Bhalla, as well as Suraj Srinivas, Flavio Calmon, and 𝙷𝚒𝚖𝚊 𝙻𝚊𝚔𝚔𝚊𝚛𝚊𝚓𝚞, which was just accepted to NeurIPS 2024! Check out the paper here: arxiv.org/abs/2402.10376

Attempting to turn my personal twitter account into an academic one. Wish me luck!

Super excited to share our latest preprint that unifies multiple areas within explainable AI that have been evolving somewhat independently: 1. Feature Attribution 2. Data Attribution 3. Model Component Attribution (aka Mechanistic Interpretability) arxiv.org/abs/2501.18887

‼️🕚New paper alert with Usha Bhalla: Leveraging the Sequential Nature of Language for Interpretability (openreview.net/pdf?id=hgPf1ki…)! 1/n

are bagels supposed to be sweet?