
Adithya Bhaskar
@AdithyaNLP
Followers
300
Following
135
Media
23
Statuses
50
Second Year CS Ph.D. student at Princeton University (@princeton_nlp), previously CS undergrad at IIT Bombay
Princeton, NJ
Joined June 2023
Ever wished circuit finding was more precise, efficient, and scalable? Now it is!.In our new preprint, we propose Edge Pruning, a conceptually simple yet effective way to find circuits in models. Details in š§µ!.Work done with @_awettig @danfriedman0 @danqi_chen 1/6
1
21
122
RT @ChengleiSi: Are AI scientists already better than human researchers?. We recruited 43 PhD students to spend 3 months executing researchā¦.
0
162
0
Paper also has (1) ablation & sensitivity studies (2) PruLong for pretraining (3) more idealized & real (hardware) metrics!. Paper: Code: Special thanks to my coauthors @_awettig @YiheS5 @gaotianyu1350 @danqi_chen!. 7/7.
0
0
4
RT @xiye_nlp: š¤ Recent mech interp work showed that retrieval heads can explain some long-context behavior. But can we use this insight forā¦.
0
17
0
RT @cindy_x_wu: Introducing COMPACT: COMPositional Atomic-to-complex Visual Capability Tuning, a data-efficient approach to improve multimoā¦.
0
44
0
RT @cindy_x_wu: Want to train large vision-language models but drowning in data? Introducing ICONS - we demonstratā¦.
0
62
0
RT @tyleryzhu: Have you ever wondered why we donāt use multiple visual encoders for VideoLLMs? We thought the same! . Excited to announce oā¦.
0
12
0
RT @noamrazin: Past work observed that DPO often decreases the probability of preferred responses. So where does the probability go? š§. Weā¦.
0
15
0
RT @HowardYen1: Come check out our poster at #ACL2024! I will be at the 4pm poster session, stop by to chat about long-context models httpsā¦.
0
4
0
RT @danfriedman0: How can we understand neural chatbots in terms of interpretable, symbolic mechanisms? To explore this question, we constrā¦.
0
30
0
RT @SadhikaMalladi: My new blog post argues from first principles how length normalization in preference learning objectives (e.g., SimPO)ā¦.
0
22
0