Official account of Yale University Computer Science.
Advancing research, education, & innovation in computing.
Follow for updates, news, events, & more
Happy to report on our Deep Learning Theory and Applications team (Comp Sci 4520/5520) at Yale! The class 75 students, approx 25 auditors. It featured the gamut of content from SGD to diffusion models to LLMs to NTKs. The raw scores of most of the class was >90%!! The projects ranged from deep learning systems for predicting wildfires, to single cell data, to electric circuit simulations. Exciting stuff! Thanks to my class students and teaching team: @Siddharth2814 Jake Kovalic, @KeXU0828@XingzhiSun!
Come see our work and talk to us at @NeurIPSConf !
Main conference:
HiPoNet: A Topology-Preserving Multi-View Neural Network For High Dimensional Point Cloud and Single-Cell Data. https://t.co/XWlTnNTrxw
HELM: Hyperbolic Large Language Models via Mixture-of-Curvature Experts." https://t.co/09BqKZjpQj
Workshops:
Invited talk at Non-Euclidean Foundation Models https://t.co/WIuptS2SBS
(Unireps/Neureps) Measure Before You Look: Grounding Embeddings Through Manifold Metrics https://t.co/Brhi1ROA2I
(FM4LS) CellSpliceNet: Explainable Multimodal Transformers for Splicing in C. elegans Neurons https://t.co/yrGwpA092V
..(in addition to the TAG-DS papers---earlier tweet)
The 2025 Yale Faculty Innovation Awards honor academic founders whose startups—rooted in Yale research—are advancing breakthroughs in health, sustainability, and engineering.
Meet the awardees: https://t.co/TUHsv7FKXk
C2S is now open for everyone.
The biological LLM that learns the language of cells. Free for academic and commercial use.
https://t.co/I2OYXmQ0x3
Join the growing community building with C2S. 🌱
(1/N) Thrilled to share that our paper HiPoNet (High dimensional Point cloud Network) to be presented at NeurIPS 2025! HiPoNet treats an entire high-dimensional point cloud as a datapoint! It captures multi-scale geometry and topology of the cloud perform classification and regression tasks. Applicable to massive biological cohorts where each sample is a whole dataset.
Exciting collaboration of the @david_van_dijk's lab with @Google — applying large-scale AI models to generate and test new biological hypotheses, advancing the intersection of computing and life sciences! 📷📷
An exciting milestone for AI in science: Our C2S-Scale 27B foundation model, built with @Yale and based on Gemma, generated a novel hypothesis about cancer cellular behavior, which scientists experimentally validated in living cells.
With more preclinical and clinical tests, this discovery may reveal a promising new pathway for developing therapies to fight cancer.
Our paper “What Makes Treatment Effects Identifiable? Characterizations and Estimators Beyond Unconfoundedness” received the Best Paper Award at COLT 2025!
Huge shout-out to my amazing collaborators: Alkis Kalavasis, Katerina Mamali, @AnayMehrotra, and Manolis Zampetakis.
Honored to receive the @NSF CAREER Award for my project on Neural Operator Learning for Biomedical Discovery! A huge thank you to my students, collaborators, mentors, and @Yale for their unwavering support! #NSFCAREER@YaleCSDept@YaleEngineering@YaleCardiology@YaleMed
https://t.co/u4loMEUL07
We’re announcing the 87 professors selected for the 2025 Google Research Scholar Program — join us in congratulating these exceptional recipients and learn more about their groundbreaking work at https://t.co/sIoedpv9pI.
#GoogleResearch#GoogleResearchScholar
Me and @ZiyaoShangguan will be at @iclr_conf in Singapore this week to present our work 🍅 TOMATO for evaluating video understanding capabilities of MFMs.
🎇Poster: 10 am -- 12:30pm at Hall 3 + Hall 2B #73, Apr 24.
If you are interested in MFMs and multimodal reasoning, let's chat!!
🍅arXiv: https://t.co/2l79AOtn2f
We will be presenting Intelligence at the Edge of Chaos at #ICLR2025. Come visit our poster!
🖼️ Poster: https://t.co/R95o1WEj6r
📜 Paper: https://t.co/nnLMDkzwtx
What if LLMs could “read” & “write” biology? 🤔
Introducing C2S‑Scale—a @Yale + @GoogleAI@GoogleDeepMind collab: we scaled LLMs (up to 27 B!) to analyze & generate single‑cell insights by turning transcriptomes into text 🧬➡️📝
🔗 Blog: https://t.co/3GbnXbKVmb
🔗 Preprint: https://t.co/beO8Z9CESc
#SingleCell #AI #LLM
Yale Computer Science Graduate Student Awards for 2024:
Congratulations to @ferhaterata for Distinguished Teaching Award, and Jim Zhou for the Distinguished Service Award! 🎉👏
#Yale@YaleEngineering
🚨 The 8th annual Graph Signal Processing Workshop is back this May 14-16! Held in Montreal, CA, at @Mila_Quebec, we’re covering all things graphs, signals, learning, & applications 🕸️〰️
🔗: https://t.co/s5olwuXvt7
👉🏻Abstract submission opens Feb 1
👉🏻 Registration opens Mar 20
Today we’re announcing the recipients of our LLM Evaluation research grants. These four projects will each receive $200K in grant funding from Meta to further their work in novel new work in evaluations over the next year.
1️⃣MMRLU: Massive Multitask Regional Language Understanding — @ABosselut, @EPFL
2️⃣Evaluating and Advancing Complex, Real-world Reasoning in Large Language Models — @armancohan, @Yale
3️⃣Modular Multi-modal Agents that Can Reason — @georgiagkioxari, @Caltech
4️⃣CodeArena: A Diverse Interactive Programming and Code Reviewing Environment for Evaluating Large Language Models — @saikatdutta2012, @CornellCIS
Congratulations to the grant recipients, we look forward to your progress in this space in 2025!