Terry Kim

@ucberkeley, @berkeleyML

[Terry Kim @thtrkim]

I had a fun time writing a deep dive on Diffusion Language Models - with an equation walkthrough and Excalidraw sketches ✏️

In Part 1, I focused on the method: what does “noise” even mean for text, and how do DLMs denoise back into tokens?

https://t.co/G8zSWCesB3

[Terry Kim @thtrkim]

@ssahoo_ @diffusion_llms Will do!

[Terry Kim @thtrkim]

I had a fun time writing a deep dive on Diffusion Language Models - with an equation walkthrough and Excalidraw sketches ✏️

In Part 1, I focused on the method: what does “noise” even mean for text, and how do DLMs denoise back into tokens?

https://t.co/G8zSWCesB3

[Terry Kim @thtrkim]

@ssahoo_ Thank you for the amazing works!

[Terry Kim @thtrkim]

@ssahoo_ Thank you for the shotout! Yes of course! I will add to my list. I was also planning to go through “esoteric language model” and “Remasking discrete diffusion models with inference-time scaling”

[Terry Kim @thtrkim]

@msikic 💪

[Terry Kim @thtrkim]

Vessl provides a great platform

[Lucas Sangdae Nam @lucas_nam96]

Are you looking for GPU credits for your next research project? @vesslai will be in San Diego for @NeurIPSConf , so if you're interested in GPU credits, feel free to sign up for a meeting here: https://t.co/XqX0sh0d3f.

Hope to see you there!

#NeurIPS #NeurIPS2025 #GPU #VESSLAI

[Terry Kim @thtrkim]

@msikic @NeurIPSConf @TinVlasic I did - thank you so much :)

[Terry Kim @thtrkim]

@msikic @RJPenic @TinVlasic @ywan_wan Hi Professor Sikic! I’ve been working on interpretability for RNA Language Models, and my results further show that RiNALMo captures structural features at the token level (e.g., hairpins). I’m currently at NeurIPS-would you have a few minutes to chat? I’d love to discuss more

[Terry Kim @thtrkim]

Heading to #NeurIPS in San Diego (AI4Science Workshop) to present our expanded RNA secondary structure dataset with structure-aware train–test splits for improved scalability and robustness.
Preprint:
https://t.co/B32qLylr0a
Dataset: https://t.co/ULkp8LirEj

Come say hi!

[Terry Kim @thtrkim]

@jakelee0711 @CompOncMSK @MSK_DeptOfMed Congrats!!

[Namrata Anand @namrata_anand2]

👋We’re excited to launch DSG2-mini, our newest AI protein design model, now available in DiffuseSandbox⏳🎁, our new app for protein binder design. Click through to design a protein yourself! https://t.co/h8CKF4kwGI 1/

[Terry Kim @thtrkim]

I’m especially grateful to Prof. Jamie Cate and Dr. Conner Langeberg for their early guidance in helping me get involved in research. Looking forward to meeting other researchers and learning at RECOMB!
#RECOMB2025 #EMBC2025 #AI4Science #MLforBio

[Terry Kim @thtrkim]

(1/5)
I’m pleased to share that my research with @seowondeog12052 has been accepted to RECOMB 2025 (Poster) and IEEE EMBC 2025 (Paper)!
Preprint: https://t.co/sW1AsKkZDL
We introduce a generative approach to pesticide design—optimizing small molecules to reduce toxicity.

[Terry Kim @thtrkim]

(4/5)

Especially want to thank the Innovative Genomics Institute for providing funding to travel and attend RECOMB 2025. And to the organizers @RECOMB_conf @IEEEembs.

[Aakarsh Vermani @aakarshv1]

Join us on Monday 3/10 for our latest installment of the BioML @ Berkeley seminar series! We'll be learning from the exceptional Elana Simon (@ElanaPearl) about mechanistic interpretability in BioML.

https://t.co/edr1KUFJ52

[EVOVA @MeTownOfficial]

MeTown is at CES 𝟐𝟎𝟐𝟓!

Come experience our hyper-realistic fashion 3D digitization service in person - EVOVA 3D ShowRoom.

📍 Booth: 𝐕𝐞𝐧𝐞𝐭𝐢𝐚𝐧 𝐄𝐱𝐩𝐨, 𝐇𝐚𝐥𝐥 𝐆, 𝟔𝟐𝟖𝟏𝟕
📧 Contact: [email protected]

#Metown #CES2025 #InnovationAward #3DRendering #ECommerce

[Alishba Imran @alishbaimran_]

Excited to share work I had the opportunity to co-lead at @czbiohub! We introduce DynaCLR, a self-supervised framework for modeling cell dynamics during perturbations via contrastive learning of time-lapse data.

https://t.co/oZZArvR6Ma

(1/11)