Arnav Goel
@_goel_arnav
Followers
282
Following
2K
Media
1
Statuses
116
MSML @mldcmu | Pre-training, alignment and memorization | ex - @MSFTResearch, @nlp_usc, @Mila_Quebec, IBM | CSAI @IIITDelhi '25
Pittsburgh, PA
Joined May 2021
✈️I will be @iclr_conf in Singapore🇸🇬 next week to present our work on attributing the cultural knowledge of a LLM to its memorization or generalization of it's pre-training corpora. Looking forward to chatting with people 🙂 #ICLR2025 . 📜:
2
7
44
RT @AdtRaghunathan: I will be at #ICML2025 🇨🇦 from Wednesday through Saturday. My students have a lot of exciting papers - check them out….
0
16
0
I just saw @_albertgu call the major AI labs as "Big Token" and it has to be the most hilarious shit ever lol.
3
17
294
RT @cloneofatharva: Anyone attending ICML 2025 looking to share accommodation? or have a place for another person?.
0
1
0
Especially for mundane everyday tasks which are done inefficiently due to a) inconsistency of; b) inaccessibility to intelligence (or expertise). I am not sure hence if the way forward for achieving this is better domain-specific expertise (which is ironical for AGI lol).
1
0
1
While AGI is an ill-defined term, an interesting measure of its achievement could be how it democratizes intelligence, fostering greater consistency across diverse human intelligence.
1
0
3
Was lucky to had gotten an early peak at this and have been waiting for it to go public. Really cool work!.
How can we unlock generalized reasoning?. ⚡️Introducing Energy-Based Transformers (EBTs), an approach that out-scales (feed-forward) transformers and unlocks generalized reasoning/thinking on any modality/problem without rewards. TLDR:.- EBTs are the first model to outscale the
0
0
6
RT @ravian_42: The extreme classification team at MSR India ( is looking for an undergraduate student interested in….
0
4
0
Had some of the best months of my college life here. Highly recommend people to register for this!!.
Announcing the Microsoft Research India Academic Summit 2025. Microsoft Research (MSR) India Academic Summit is an event aimed at strengthening ties between the Indian academic community and researchers at MSR India. 📅 Event Dates: June 24th & 25th.
0
0
3
Who thought having the NeurIPS and EMNLP deadline a couple of days apart was a good idea 😭.
2
1
1
Damn nice.
We’ve developed Gemini Diffusion: our state-of-the-art text diffusion model. Instead of predicting text directly, it learns to generate outputs by refining noise, step-by-step. This helps it excel at coding and math, where it can iterate over solutions quickly. #GoogleIO
0
0
0
RT @xiangrenNLP: Proud of my student @huihan_li and intern Arnav presenting their #ICLR2025 work on attributing culture-conditioned generat….
0
6
0
RT @amt_shrma: PywhyLLM: Creating an API for language models to interact with causal methods and vice versa. v0.1 out, welcome feedback.….
0
14
0
Starting now in Hall 3 (#255). Drop by if you want to chat about memorization, culture or just LLMs in general :).
✈️I will be @iclr_conf in Singapore🇸🇬 next week to present our work on attributing the cultural knowledge of a LLM to its memorization or generalization of it's pre-training corpora. Looking forward to chatting with people 🙂 #ICLR2025 . 📜:
0
0
7
RT @amt_shrma: What changes for causality research in the age of LLMs and what does not? Enjoyed this conversation with Alex Molak on how L….
0
7
0
RT @huihan_li: I will be presenting our @iclr_conf paper on attributing culture conditioned generations to memorization of pretraining data….
0
4
0
RT @AniketVashisht8: Excited to present our work in ICLR this week on LLMs and Causality!. We try to answer the question: How can imperfect….
0
4
0