1. Paper on "Neural Network Pruning for Real-time Polyp Segmentation" investigates a novel network pruning method for reducing the parameter count and FLOPs retaining the performance of the original network. Congrats to Rough Researcher Sudarshan Regmi '(Bibek Panthi) and Pranav.

Try to be nice, but never forget to be kind. - The 12th Doctor

[THREAD: Brendon McCullum & 3 Controversial(?) Run Outs] Bulawayo 2005: Chris Mpofu got run out while celebrating his partner's 50. (1/4)

Well, well, well 🧐 “It’s within the rules of the game and that’s how it is!” - Bairstow 2014 #Bairstow #Ashes23 Thanks for the heads up Diana Yallop Voted YES. 👏

Spirit of the game 🤣 Obedient disciple : Bairstow

Yesterday I was working on a formalization of something in VS code with GitHub copilot on, talking with a collaborator while sharing my screen over zoom. We finished a theorem, and started discussing what the next natural theorem is. Copilot suggested the complete statement and

this paper's nuts. for sentence classification on out-of-domain datasets, all neural (Transformer or not) approaches lose to good old kNN on representations generated by.... gzip aclanthology.org/2023.findings-…

Our new paper improves genetic risk predictions by learning disentangled representation for ancestry and disease nature.com/articles/s4200… W/ applications to #alzheimersdisease. Great job led by Prashnna K Gyawali and Zihuai He 👏

We are just two days away from our #MICCAI2023 workshop. Meet our renowned Keynote Speakers, Prof. James Zou and Prof. Qi Dou. Get ready to be inspired by their groundbreaking work and insights.Binod Bhattarai @sharib Razvan Caramalau @arau312 Dan Stoyanov @

We have a great line-up of Keynote speakers and excellent papers addressing various problems in data engineering in medical imaging. Come join us in Room 3, Level 1, Vancouver Convention Centre tomorrow. You can find the proceedings of the workshop: link.springer.com/conference/demi

I plan to take on graduate students 🎓 working on Computer Vision 📷, AI 🧠, & Robotics 🤖 in U of T Department of Computer Science. Interested in joining and becoming part of the broader University of Toronto Robotics Institute and Vector Institute communities? Learn more at sgs.utoronto.ca/programs/compu… 1/2

Sudarshan Regmi is on fire. He presented 2 papers back-to-back on Trusted Computer Vision workshop at #CVPR2024. Very well done!

“mathematical breakthroughs are not powered solely (or even primarily) by ‘Eureka’ moments of genius, but are in fact largely a product of hard work” —Terry Tao terrytao.wordpress.com/career-advice/…

Easy way to fix academia: Add a negative offset to all citation counts in Google Scholar. Every new paper starts at -100 citations and has to claw its way out of that hole.

"Judge talent at its best but character at its worst." — Lord Acton

Really enjoyed my recent talk with Joe The Human Podcast in a casual conversation about work and life. youtube.com/watch?v=Fpef7L…

🔥Your Weak LLM is a Secret Alignment Powerhouse! Scaling alignment with pure human or AI feedback (GPT-4) isn't cheap 💸. It demands enormous human effort or computing power. Our new study reveals a hidden gem: even weak LLMs with just 125M parameters can provide powerful

Spent the past two days learning Mamba, SSM, and relevant concepts. The outcome is this written note "Exploring Mamba: A High-Level Guide to State Space Models" link.medium.com/8PSRRoIjlPb. Kindly check it out if interested!

We're organzing the "Quantify Uncertainty and Hallucination in Foundation Models" workshop at #ICLR2025! 📢 Call for Papers: Submit your work by February 2, 2025 (AOE). 🔗 More details: …certainty-foundation-models.github.io Look forward to seeing your submission and participation in the

Agency > Intelligence I had this intuitively wrong for decades, I think due to a pervasive cultural veneration of intelligence, various entertainment/media, obsession with IQ etc. Agency is significantly more powerful and significantly more scarce. Are you hiring for agency? Are