Very nice!
12.04.2025 05:19 โ ๐ 0 ๐ 0 ๐ฌ 0 ๐ 0@rahulapanicker.bsky.social
Founder CEO @ stealth robot-learning startup | prev AI/robots @intrinsicAI (GOOGL) @vicariousAI (acq), co-founder Embrace | MIT TR35 | Stanford PhD, IIT Madras
Very nice!
12.04.2025 05:19 โ ๐ 0 ๐ 0 ๐ฌ 0 ๐ 0I am looking for a postdoc candidate. Here are some details. Could you please help me spread the word? Thanks! Application deadline: April 22, 2025.
candidate.hr-manager.net/ApplicationI...
@jay.bsky.team @support.bsky.team Can something please be done about these?
26.03.2025 04:11 โ ๐ 0 ๐ 0 ๐ฌ 0 ๐ 0Congratulations! ๐
22.03.2025 23:08 โ ๐ 1 ๐ 0 ๐ฌ 0 ๐ 0These typically work when the graph structure is assumed, and parameters are learned. Eg for question โ robot is being trained to cook. Grasping, placing, cutting, sprinkling, mixing, measuring are all tasks that apply across multiple ingredients, mixtures, or dishes. Data is 3D voxel-labeled video.
21.03.2025 19:29 โ ๐ 1 ๐ 0 ๐ฌ 0 ๐ 0Thank you!
21.03.2025 19:13 โ ๐ 1 ๐ 0 ๐ฌ 0 ๐ 0Trying my luck here: compositionality in learning. Automated decomposition of sequential tasks into modules that can be composed.
21.03.2025 19:12 โ ๐ 2 ๐ 0 ๐ฌ 1 ๐ 0Structured analysis of hidden convexity. What are problems where it is possible, how to sniff them out, good reviews, etc.
21.03.2025 19:10 โ ๐ 1 ๐ 0 ๐ฌ 1 ๐ 0Yep, Iโll go on a limb and say impossible to imagine.
20.03.2025 21:56 โ ๐ 1 ๐ 0 ๐ฌ 0 ๐ 0Yep! Same reason applies for composition.
09.03.2025 03:17 โ ๐ 1 ๐ 0 ๐ฌ 0 ๐ 0One might argue that it is closed form if one can do analysis and algebra on it. Composition, derivatives, etc.
07.03.2025 22:52 โ ๐ 1 ๐ 0 ๐ฌ 1 ๐ 0#OTD Indian physicist C. V. Vishveshwara(1938-2017) was born. Vishveshwara made many important contributions to general relativity.
His seminal contribution was the discovery of quasi-normal modes in black holes.โ๏ธ
Black hole man of India. His book was delightful.
07.03.2025 05:25 โ ๐ 2 ๐ 0 ๐ฌ 0 ๐ 0How cool!
07.03.2025 05:19 โ ๐ 1 ๐ 0 ๐ฌ 0 ๐ 0A touch of self-advertisement: I'll be giving a research talk next Tuesday at the Online Monte Carlo Seminar (sites.google.com/view/monte-c...) on one of my favourite topics: the convergence properties of the Random Walk Metropolis algorithm. Please join us!
14.02.2025 16:31 โ ๐ 43 ๐ 9 ๐ฌ 1 ๐ 1Whoa! ๐
14.02.2025 19:56 โ ๐ 0 ๐ 0 ๐ฌ 0 ๐ 0Whatโs the backstory?
10.02.2025 18:16 โ ๐ 0 ๐ 0 ๐ฌ 1 ๐ 0Congratulations, Yoshua!
05.02.2025 22:12 โ ๐ 0 ๐ 0 ๐ฌ 0 ๐ 0