![Irhum Shafkat Profile](https://pbs.twimg.com/profile_images/1407171251731263504/sP9rNsSg_x96.jpg)
Irhum Shafkat
@irhumshafkat
Followers
823
Following
4K
Statuses
556
Mostly in the weird alleys where fields meet, trying to find the right questions
San Francisco, CA
Joined May 2017
RT @rohitsingh8080: Have been thinking about ESM-3. Lots to like, some not so much. With a mug of station-wali chai on a drizzly Saturday m…
0
22
0
RT @siyan_zhao: Have you wondered how the decision boundary of in-context learning in LLMs compares to traditional models like Decision Tre…
0
203
0
RT @alexrives: After we trained ESM3, we were excited to see it could respond to complex prompts, which greatly improved with scale. While…
0
36
0
RT @orvieto_antonio: NGN introduces a new paradigm for optimization in deep learning: cheap curvature estimation with state-of-the-art theo…
0
55
0
RT @tokenpilled65B: We present Unified Masked Diffusion (UMD), a self-supervised objective that trains a ViT based auto-encoder for downstr…
0
47
0
RT @olivierhenaff: Thrilled to announce our latest work on active data curation: joint example selection (JEST) drastically accelerates lar…
0
50
0
RT @alexrives: We have trained ESM3 and we're excited to introduce EvolutionaryScale. ESM3 is a generative language model for programming…
0
827
0
RT @bkmi13: Announcing our new model for materials! FlowMM... - Generates stable & novel materials efficiently - Predicts crystal structu…
0
68
0
RT @shreyaskapur: My first PhD paper!🎉We learn *diffusion* models for code generation that learn to directly *edit* syntax trees of program…
0
615
0
RT @SynBioBeta: AI scientist Alex Rives @alexrives states that the code of life is becoming programmable and takes a closer look at protein…
0
11
0
RT @aaron_defazio: Schedule-Free learning replaces the momentum of the base optimizer with a combination of averaging and interpolation, to…
0
16
0
RT @aryaman2020: New paper! 🫡 We introduce Representation Finetuning (ReFT), a framework for powerful, efficient, and interpretable finetu…
0
103
0
RT @jeremyphoward: Here, in full directly on Twitter, is "A Hackers' Guide to Language Models". This 90 minute tutorial is designed to be t…
0
1K
0
RT @Theteamatx: “AI is only part of the solution. The important thing is the ‘connective tissue’ all around it that connects it to the real…
0
4
0
Really grateful to @drjwrae, @erich_elsen, @klarakaleb, @garretthonke and @JonJonDeats for their feedback, as well as thoughtful discussions that led to this.
0
0
5