Toby Mao

M1 @StanfordMed and @KnightHennessy | Research @StanfordAILab and @arcinstitute | Previously @FulbrightPrgrm

[Toby Mao @tobymm25]

@jadenvclark Great work Jaden!

[Jaden Clark @jadenvclark]

Can we enable robots to develop a sense of touch without forgetting what they learned from large-scale vision-only pretraining?

Introducing MultiSensory World Model (MuSe) 🌍: A new approach for finetuning visuomotor policies on minimal data from new sensor modalities, such as force/torque (F/T)

With Muse, touch learned later improves skills learned earlier — a small amount of F/T data on new tasks improves zero-shot on diverse pretraining tasks that were never supervised with F/T

We believe MuSe provides a practical pathway towards training multisensory foundation models that leverage both abundant vision data, and smaller multisensory datasets 🧵👇

[Toby Mao @tobymm25]

@yusufroohani @arcinstitute Congrats Yusuf and thanks for all of your mentorship

[Toby Mao @tobymm25]

@claudeai Can someone make a benchmark on the efficiency-accuracy of coding agents (how much token burnt for a task and accuracy of the task)? I am low on tokens

[Sophia Pribus @sjpribus]

"The erosion of creative thinking means young people will struggle to navigate uncertainty." AI can only iterate on what it has seen before- but "our species’ ability to come up with unexpected and original ideas is something to protect and nurture." https://t.co/6AUb9MECNR

[Toby Mao @tobymm25]

@brennan__simon Real data reflects the true distribution of language and knowledge, while synthetic data is just a recursive projection of the prior that current models already believe. The improvement is marginal and could risk long-tail problem that would result in model collapse.

[Toby Mao @tobymm25]

@brennan__simon Cautiously optimistic. In training LLM, syn data is usually used in post-training, especially in finetuning reasoning whereas real data predominates pre-training. However, in biomedical research, the bottleneck is scarcity of real data that represent diverse biology.

[Toby Mao @tobymm25]

@Roth_Lab @AustinMHartman congrats @austinhartman

[Roth_Lab @Roth_Lab]

Genome wide perturb seq creates powerful perturbations x transcripts datasets. This unveils new biology - but also reveals new off-target effects. New work from @AustinMHartman, a massively talented PhD student in our lab, systematically identifies seed driven off-target effects in genome-wide perturb seq exps. (1 of 3) https://t.co/6kg7cJjCQr

[Arc Institute @arcinstitute]

The next inflection point in virtual cell modeling will require large-scale perturbative data. To get there we are partnering with @tahoe_ai and @officialbiohub to help us generate a dataset to push us forward: https://t.co/dZbcKBTxdX

[Toby Mao @tobymm25]

Link to full interview:
https://t.co/xVONGDN99e

https://t.co/ZCJWmXKoVL

[Toby Mao @tobymm25]

How do we move beyond chain-of-thought to build models that reason more deeply and reliably?
Is generalization, rather than scale, now the real bottleneck?
I’m excited to talk with @Muennighoff, on the frontier of model reasoning and reinforcement learning.
#ai #LLMs #reasoning

[Toby Mao @tobymm25]

@Muennighoff Niklas Muennighoff:
https://t.co/kPD9awoOFG
https://t.co/GtQnKflDgV

[Toby Mao @tobymm25]

In this conversation, we discuss:

Model reasoning research beyond chain-of-thought

The future of reinforcement learning

Test-time scaling and inference-time compute tradeoffs

AI’s impact on the job market, the “AI bubble,” and separating signal from hype

[Toby Mao @tobymm25]

#virtualcell #ai #aihealth

[Toby Mao @tobymm25]

In Silicon Valley, “virtual cells” are suddenly everywhere.

Meta and CZI recently went all in, signaling that this is no longer a fringe research direction.

So what is virtual cell? Check out my new blog about virtual cell: https://t.co/lQx2dc4XsZ

[Toby Mao @tobymm25]

Thanks so much for this opportunity for me and @_AravindK_ Dr. Kohane, looking forward to future collaborations!

[Isaac Kohane @zakkohane]

Thanks to the bright and highly motivated @Stanford students who met me for the #PitchMe for @NEJM_AI @CoupaCafe

[Johns Hopkins Neuro-Oncology Surgical Outcomes Lab @NeuroOncSurgery]

We've got a #Twofer for #TT!! First, we tested 6 different #ML models for Grade IV #glioma prognosis, with improvement after feature selection and high accuracy.

They identified factors such as adjuvant TMZ💊, confusion, and MGMT status🧬 as predictive in survival!

[Christopher Nguyen, PhD, FSCMR, FACC @ChrisNguyenPhD]

Today is a bittersweet moment with Toby Mao leaving my group and pursing his next step as a prestigious @FulbrightPrgrm fellow as he waits to hear back from med schools. Congratulations to Toby and we wish him luck!

@CleClinicCIRC @CleClinicHVTI