Satpreet Singh
@tweetsatpreet
Followers
3K
Following
13K
Statuses
2K
AI/ML/Simulation x Neuro/Bio Postdoc @KanakaRajanPhD @harvardmed @KempnerInst; PhD @UW; Ex @Meta @LinkedIn @Orbitz @TXInstruments.
🌎
Joined October 2010
1/n Excited to share our new preprint where we study turbulent plume tracking using deep reinforcement learning (DRL) trained RNN *agents* and find many intriguing similarities with flying insects. w/ @FlorisBreugel @RajeshPNRao @bingbrunton; #tweeprint @flypapers #Drosophila
8
41
177
RT @KempnerInst: What can weakly electric fish teach scientists about #NeuroAI? Read about how #KempnerInstitute’s @KanakaRajanPhD is study…
0
7
0
RT @EugeneVinitsky: We've built a simulated driving agent that we trained on 1.6 billion km of driving with no human data. It is SOTA on e…
0
99
0
RT @MAG2ART: A cell with 3 nuclei (cyan) videoed through a microscope. Mitochondria (yellow) and the actin cytoskeleton (red) are also show…
0
251
0
RT @KanakaRajanPhD: Delighted to have a chance to contribute to @_TheTransmitter’s debut book! I highlight how noise in the brain could act…
0
10
0
RT @SuryaGanguli: Absolutely. In any hypothesis test between A and B about the working of a complex system, the right answer is invariably…
0
20
0
RT @scott_linderman: If you'd like to learn more about parallelizing nonlinear RNNs, check out our blog post! It goes step by step through…
0
5
0
RT @rohanpaul_ai: Brilliant paper from @Meta having the potential to significantly boost LLM's reasoning power. Why force AI to explain in…
0
328
0
RT @KempnerInst: College grads interested in intelligence research: the application for #KempnerInstitute's post-bac program w/ the @Harvar…
0
5
0
RT @sirbayes: I am happy to announce that the first draft of my RL tutorial is now available.
0
759
0
RT @scott_linderman: Did you know that you can parallelize *nonlinear* RNNs over their sequence length!? Our @NeurIPSConf paper "Towards Sc…
0
31
0
RT @patrickmineault: Excited to release what we’ve been working on at Amaranth Foundation, our latest whitepaper, NeuroAI for AI safety! A…
0
95
0
RT @memming: Innovations by many in the history of AI. Shun-ichi Amari's important contributions shall not be forgotten. (I made this slide…
0
12
0
RT @jwthickstun: I am recruiting PhD students for Fall '25 at Cornell! I plan to admit multiple students interested in building more contro…
0
49
0
RT @ShamKakade6: (1/n) 💡How can we speed up the serial runtime of long pre-training runs? Enter Critical Batch Size (CBS): the tipping poin…
0
31
0
RT @MarlosCMachado: RLC will be held at the Univ. of Alberta, Edmonton, in 2025. I'm happy to say that we now have the conference's website…
0
37
0
RT @ClementBonnet16: Introducing Latent Program Network (LPN), a new architecture for inductive program synthesis that builds in test-time…
0
33
0
RT @VincentMoens: Today we're opensourcing a LeanRL, a simple RL library that provides recipes for fast RL training using torch.compile and…
0
39
0
RT @sirbayes: I'm happy to announce our new review paper on methods for online prediction (and segmentation) in the presence of non-station…
0
46
0