Reza Samavi

Associate Professor, Electrical & Computer Engineering @TMU_ecbe Faculty Affiliate @VectorInst

[Accepted papers at TMLR @TmlrPub]

Superposition as Lossy Compression — Measure with Sparse Autoencoders and Connect to Adversarial ...

Leonard Bereska, Zoe Tzifa-Kratira, Reza Samavi, Stratis Gavves.

Action editor: Pin-Yu Chen.

https://t.co/oiZAYW1l03

#autoencoder #superposition #ne

[Amir Rosenfeld @AmirRosenfeld]

VLMs (GPT-4o, Gemini, Qwen-VL, LLaVA…) look impressive — until you shift an image by 1 pixel.
A tiny, meaning-preserving change → a completely different answer.
This isn’t adversarial — it’s natural variation.
Watch 👇

[Gautam Kamath @thegautamkamath]

Check out the amazing @let4all Mentorship Workshop happening in just two weeks!

Theme: Harnessing AI for Research, Learning, and Communicating

Featuring an amazing lineup of speakers and also hands-on experience with ChatGPT Pro to see how to use AI to help your research.

[Reza Samavi @RezaSamavi]

Congratulations to my PhD student Hirad Daneshvar for successfully defending his thesis on "Trustworthy Graph Neural Networks for Healthcare Predictive Modelling." Bravo Dr. @Hirad_Daneshvar ! @FEAStorontometu @TMU_ecbe @VectorInst

[Reza Samavi @RezaSamavi]

Check our recent paper on a precise and efficient method of quantifying GNNs predictive uncertainty, appearing at AIiH'25: https://t.co/xagxBrZtMX.
@Hirad_Daneshvar @TMU_ecbe @VectorInst @FEAStorontometu

[Reza Samavi @RezaSamavi]

We addressed this in our paper https://t.co/vwj8ux9f92 in
@midl_conference by devising a spatially aware CP function that incorporates the varying importance of regions in a segmentation task with applicability to other fields. #MIDL2025 @VectorInst @researchTMU @TMU_ecbe

[Reza Samavi @RezaSamavi]

Conformal Prediction (CP) is a nice and (almost) assumption-free framework for quantifying uncertainty by constructing prediction sets with finite-sample coverage guarantees. @thehdmx

[Reza Samavi @RezaSamavi]

However, the set generated by the classical CP, with a rigid score function, is unable to capture the varying importance of the prediction set, which has adverse implications for confidence measurement in image segmentation or risk control in navigating robots. @CancerCenterAms

[Reza Samavi @RezaSamavi]

@thehdmx @Hirad_Daneshvar @MrezaMaleki_95 @VectorInst @thegautamkamath @TMU_ecbe thanks @dev1cenet . here are our 2 recent papers on this topic:
https://t.co/4NmxYBiRxy
https://t.co/avhAlU4I1e
and two more from last year:
https://t.co/N0hMO6LFeS
https://t.co/GNlA8rT4SD

[Reza Samavi @RezaSamavi]

Another well-organized and successful ML Security and Privacy workshop. Active TAILab participation with posters on Uncertainty quantification (@thehdmx @Hirad_Daneshvar) and Certified robustness (@MrezaMaleki_95) . Thanx to @VectorInst @thegautamkamath @TMU_ecbe

[Learning Systems and Robotics Lab (is hiring!) @learnsyslab]

How can a robot traverse crowds of people? Checkout this press release about our crowd navigating robot.
https://t.co/avrOWsHG6J

[TU München @TU_Muenchen]

Jack, a wheeled #robot from our university, navigates crowds by predicting people’s paths and adjusting 10 times per second. Rather than stopping, it adapts smoothly to avoid collisions: https://t.co/plm1CBWGWx

#RoboticsInstituteGermany #AutonomousVehicles #AI

📷A. Eckert

[Harshleen @0xharshleen]

17 platforms where you can begin cybersecurity🚀

1. HackXpert - Free labs and training.
2. TryHackMe - Hands-on exercises and labs.
3. CyberSecLabs - High quality training labs.
4. Cybrary - Videos, labs, and practice exams.
5. LetsDefend - Blue team training platform.
6. Root Me - Over 400 cybersecurity challenges.
7. RangeForce - Interactive and hands-on platform.
8. Certified Secure - Loads of different challenges.
9. Vuln Machines - Real world scenarios to practice.
10. Try2Hack - Play a game based on the real attacks.
11. TCM Security - Entry level courses for cybersecurity.
12. EchoCTF - Train your offensive and defensive skills.
13. Hack The Box - Cybersecurity training platform.
14. Vuln Hub - Material for hands-on experience.
15. OverTheWire - Security concepts via challenges.
16. PentesterLab - Learn web-app penetration testing.
17. PortSwigger Web Security - General learning.

credit-Daniel Kelley

[Kyunghyun Cho @kchonyc]

i like both AI and end-to-end encryption. can i have them all? we examine this question carefully in <How To Think About End-To-End Encryption and AI: Training, Processing, Disclosure, and Consent> by Knodel, Fabrega, Ferrari, Leiken, Hou, Yen, de Alfaro, Cho and Sunoo Park.

[Learning Systems and Robotics Lab (is hiring!) @learnsyslab]

Happy Robotic Holidays from the Learning Systems and Robotics Lab! Episode 1: Delivering Gifts.
Video: https://t.co/saTd0hO08t

[Sepehr Samavi @SepehrSamavi]

Checkout our robot getting ready for the holidays using SICNav to move around!
Video: https://t.co/V4HzKXOlX3
Paper: https://t.co/2GmFUqT6Yt

[Reza Samavi @RezaSamavi]

Congratulations Dr. Mini Thomas! A long successful journey and a big celebration day! @McMasterEng @McMasterU @TMU_ecbe

[Sepehr Samavi @SepehrSamavi]

Our latest work Safe and Interactive Crowd Navigation (SICNav) has been accepted to @ieeeTRO! SICNav jointly solves planning and prediction while satisfying safety consts! Thanks @florian_shkurti @angelaschoellig

preprint & code: https://t.co/2GmFUqSz8V

https://t.co/J75yCZMvNz

[Reza Samavi @RezaSamavi]

@ebrahim_bagheri @researchTMU @TorontoMet @CIHR_IRSC @A_Tavallaei @FEAStorontometu @arts_tmu Congrats Ali!

[Vector Institute @VectorInst]

.@thegautamkamath and his team have shown that the best robust estimators often translate to the best private estimators. This connection has important implications for designing statistical methods. Check it out below⬇️

https://t.co/9d9C3T4CXC