Yongju Lee
@LeeTaliq
Followers
86
Following
156
Media
1
Statuses
141
23.02 ~ postdoc fellow @genentech (Advisor: Aviv Regev) Prev: Ph.D Seoul National University Machine learning for biomedical data
Joined February 2019
📃Don't miss the Comment now ONLINE @NatureCancer on 'How AI agents will change cancer research and oncology' by Aviv Regev, Jakob Nikolas Kather @jnkath and co-authors 🔗 https://t.co/m7mTVXtxHz featuring into our year-in-review Focus Issue!
nature.com
Nature Cancer - Deep learning models are advancing cancer research and oncology but require human engagement to perform complex multi-step workflows. Autonomous artificial intelligence agents,...
0
4
10
Very happy to share our article about AI agents in cancer research and oncology, with @LeeTaliq @Dykex6 & Aviv Regev, out in @NatureCancer now -> https://t.co/A3tZ6omeAf
@katherlab @NCT_UCC_DD @NCT_HD
2
29
113
It's one thing to have a cell atlas of the human body. It's another to build foundation #AI models, test perturbations, and establish causal effects. An insightful review/perspective @CellCellPress
https://t.co/fG725zAvSu
@jennyErood @GraphicAnja Aviv Regev @genentech
2
92
349
🚀Interested in doing a PostDoc in my lab? Consider applying for a🇨🇭SNSF Swiss Postdoctoral Fellowship 2024. If you have any questions, join the information event tomorrow via Zoom (register via https://t.co/yC7bO8ncBZ) or reach out to us via https://t.co/KyIo0ZINaK! 🧬Who
docs.google.com
When: Thursday, September 26, 2024 Time: 11:00 - 12:30 Online via ZOOM The link to the zoom meeting will be sent to you by email before the start of the session.
📢 #Call for SNSF Swiss Postdoctoral Fellowships 2024 This highly competitive call is aimed at researchers who wish to obtain a position in a non-profit research institution in Switzerland for a period of 12 to 24 months. 🗓️Deadline: 2 December 2024 https://t.co/8temO8KALg
0
22
73
How can we build an Al Virtual Cell 🔮🧬 that simulates all functions and interactions of a cell? How will it transform research and drive breakthroughs in programmable biology, drug discovery and personalized medicine? 🚀 Take a look at our Perspective! https://t.co/Pou9zG4U8v
12
128
479
Pay attention to the description of the brain regions. Also, a great summary of LLM issues to date.
Many folks often say that LLMs are just pattern matching… and contrary to some, I would actually agree with that sentiment! However, I really don’t think that scaling LLMs alone will help us breakthrough the next intelligence plateau. Surely, bigger models running faster and
8
13
139
Apple presents MUSCLE A Model Update Strategy for Compatible LLM Evolution Large Language Models (LLMs) are frequently updated due to data or architecture changes to improve their performance. When updating models, developers often focus on increasing overall performance
2
65
328
There were an insane number of "big" biotechnology papers published this week. The Bridge RNA gene-editing papers are important. But here are 7 more advances. Many new CRISPR tools, epigenetic editing for prion disease, gene drives for plants & more...🧵
9
156
860
AI & Biology/medicine is at its best time 🔥🔥exciting time ahead!
1
17
133
As LLMs have improved in their capabilities, so have their dual-use capabilities. But many researchers think they serve as a glorified Google We show that LLM agents can autonomously hack websites, showing they can produce concrete harm Paper: https://t.co/nAzkYYeUq8 1/5
Is there any known case of anyone accessing “harmful capabilities” of an LLM that didn’t consist of knowledge already freely available and clearly described in documents on the open web? Is the fear that we are basically just getting what we would already have if Google / Bing
12
101
406
Retrieval augmented generation (RAG) was proposed in 2020, but the idea has since been explored and expanded by a variety of papers. Here are four notable publications that study advanced concepts with RAG… (0) Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks:
5
89
378
Apple presents Specialized Language Models with Cheap Inference from Limited Domain Data paper page: https://t.co/RzRhwp2j5C Large language models have emerged as a versatile tool but are challenging to apply to tasks lacking large inference budgets and large in-domain training
4
84
418
Excited by the generality of CLIP, but need more fine-grained details in your representation? Introducing SPARC, a simple and scalable method for pretraining multimodal representations with fine-grained information. 🥳 1/6
7
54
303
"scPerturb: harmonized single-cell perturbation data" is out now in Nature Methods!
4
45
210
MM-LLMs: Recent Advances in MultiModal Large Language Models paper page: https://t.co/MhNNs5SD2E In the past year, MultiModal Large Language Models (MM-LLMs) have undergone substantial advancements, augmenting off-the-shelf LLMs to support MM inputs or outputs via
5
182
713
CARE talks kick off again this week, with Goutham Rajendran talking about learning disentangled representations ( https://t.co/8oGoNMHOT7). It's a really nice paper showing with linear + Gaussian latents we don't need many interventions to disentangle latents. Thursday, 11am EST
portal.valencelabs.com
We discuss the problem of learning causal representations from unknown, latent interventions in a general setting, where the latent distribution is Gaussian but the mixing function is completely ...
1
7
19
🎉🪩🎄 Check out our new PerturbView method for easy optical perturbation screens in primary cells and tissues. @TakaKud0 has written a great summary in the quoted thread. Check it out!
biorxiv.org
Optical pooled screening (OPS) is a highly scalable method for linking image-based phenotypes with cellular perturbations. However, it has thus far been restricted to relatively low-plex phenotypic...
Our preprint on the development of PerturbView, an Optical Pooled Screening (OPS) technology, is out! Massive thanks to @eric_lubeck for driving the project with me, along with our fantastic mentors, Orit Rozenblatt-Rosen, @LeviAGarraway and Aviv Regev https://t.co/MbijOGpwTX 1/
1
6
31
Our preprint on the development of PerturbView, an Optical Pooled Screening (OPS) technology, is out! Massive thanks to @eric_lubeck for driving the project with me, along with our fantastic mentors, Orit Rozenblatt-Rosen, @LeviAGarraway and Aviv Regev https://t.co/MbijOGpwTX 1/
biorxiv.org
Optical pooled screening (OPS) is a highly scalable method for linking image-based phenotypes with cellular perturbations. However, it has thus far been restricted to relatively low-plex phenotypic...
2
23
82
We are excited to announce PathChat - a vision-language AI assistant for #Pathology that can analyze histology images and answer diverse pathology-related queries. Co-led by our superstars @MYLu97 @chenbowen118 @DFKW_MD Preprint: https://t.co/JByRBT4u6Y Demo below,
31
178
609
Heroic effort by our summer intern Anay Gupta, @lauragunsalus and @lal_avantika. Also the first preprint of our group, very proud!
We’re excited to share Polygraph, a Python framework for evaluating native and synthetic DNA regulatory elements! @lal_avantika @gokcen
https://t.co/mJixAWc2Mb
0
7
62