Deepayan

work done with @davidetalon94 @YimingWang107 @@massi_manc @eliricci_

🚀 Poster day at #ICCV2025! I’ll be at Poster Session 2, Exhibit Hall I (3–5 p.m. HST) presenting: ✨ Training-Free Personalization via Retrieval and Reasoning on Fingerprints Come say hi, chat research, or just vibe! 👉 deepayan137.github.io/papers/trainin…

Working on Test-Time Adaptation (TTA) and don't know what to do after your #CVPR2025 submission? Beat this frustratingly simple baseline and secure yourself a spot in wonderful Hawaii (#ICCV2025 watch out 👀) More on our latest work accepted @NeurIPSConf in the thread!

Writing you CVPR related work on #ContinualLearning ? 🚨 Exciting News! 🚨 Our paper "One VLM to Keep it Learning: Generation and Balancing for Data-free Continual Visual Question Answering" has been accepted at #WACV! 🎉 Check it out! Arxiv: arxiv.org/abs/2411.02210

GaB not only maintains robust VQA performance across tasks but does so without historical data, matching methods that have such access. Stay tuned for the code release! 🔗📷

This a joint work with @davidetalon94 @YimingWang107 @massi_manc and @eliricci_

🤖🔍 Want to continually learn vision-language tasks without relying on external data? Check out our latest approach, GaB, now accepted at #WACV2025! It tackles catastrophic forgetting head-on. Learn more: arxiv.org/abs/2411.02210 #AI #MachineLearning

@memenist_ cv

SSR was visionary 🙏🏻

Unfortunately being rejected by @eccvconf, but believing in your works to be shared with the CV community? Working on VLMs, LLMs, MLLMs, and their efficient usage? Why not submitting to our Workshop on Green Foundation Models @Green_FOMO! More info 👉 green-fomo.github.io/ECCV2024/index…

Amazing opportunity. Do apply 😎 💪🏻

The call for Ph.D. candidates @cimec_unitrento is now open! 🎓 If you are interested in conducting research on visual reasoning using Multi-modal Large Language Models, please apply here. 🧠 👇👇👇 unitn.it/drcimec/116/ad…

Glad to announce that the 1st Workshop on Green Foundation Models (GreenFOMO) is happening @eccvconf Milan, 2024🥳 Can't wait to see what impact our community can make towards a green world 🌏and an inclusive AI💚! Official website + CfP coming soon...Stay tuned😉

@HChateauLaurent Haha… sta andando bene 😅

@johnny_deep93 Thanks Deep 🙃 Come sta tu PhD ?

Next Thursday will be a big day for me! I will defend my PhD thesis on modelling the interactions between episodic memory and cognitive control!

Enjoyed visiting UC Berkeley’s Machine Learning Club yesterday, where I gave a talk on doing AI research. Slides: docs.google.com/presentation/d… In the past few years I’ve worked with and observed some extremely talented researchers, and these are the trends I’ve noticed: 1. When starting a project, average researchers tend to jump quickly to modeling proposals, architecture design, new ideas, etc. Great researchers often first spend time manually looking at data and playing with models to deeply understand the problem, before proposing an (often simple) approach. 2. Average researchers may often write hacky code that is not reusable and requires many separate steps. Great researchers are often also great software engineers—their code can be easily extended for future experiments, they write extensive tests, and they create infra to run many experiments quickly and visualize results with the fewest clicks. 3. While average researchers might work mostly by themselves or with one or two others, great researchers know that research is a social activity. They collaborate with people of varying experience, share results in writeups, and communicate their vision convincingly. 4. Average researchers might get stuck in rabbit holes—if they have experiments with only mediocre results, they spend 3 more weeks writing it up and submitting it to a conference. Great researchers quickly move on to something else when they know that one approach won’t be a breakthrough. 5. If an average researcher finds some success, they may try to keep doing that thing they are comfortable with for several more years, even if it becomes outdated. Great researchers pivot quickly and keep adapting to new advances and paradigms. 6. Average researchers often implement task-specific solutions, which are heavily optimized for a single task. Great researchers may also work on specific tasks, but they try to think of general approaches that can be applied to many other tasks. 7. Average researchers talk about and optimize for the number of papers or conference acceptances. I have never met a great researcher that still cares about such things. (And by the way, being an average researcher shouldn’t be taken as an insult. It takes a lot of hard work to even do research at all :))

What? When? Where? An Indian men’s 4x400 relay team qualifying for the finals in the World Athletics Championship? Looks like everyone is shooting for the moon now… Look at them run…Our Cheetahs…. twitter.com/indhavaainko/s…

Extremely elated to win Silver medal 🥈in Fide World Cup 2023 and qualified to the Candidates 2024! Grateful to receive the love, support and prayers of each one of you! 🇮🇳 Thankyou everyone for the wishes🙏🏼 With my ever supportive, happiest and proud Amma❤️ 📷@M_Sridharan

The reviewer is asking us how tight our equality is.

The textbook I use for my #DeepLearning course 😍 HIGHLY recommended!!! eecs.yorku.ca/~kosta/Courses…