Tenure track Assistant Professor at University of Bergamo.
Joined April 2010
- Tweets497
- Following500
- Followers286
- Likes5.3K
Paper got rejected from #WACV. Happens, no big deal.
But what are the odds that every "reviewer" raises the exact same weakness as their very first bullet point in the weaknesses section? For context, the weakness is from the 5th page of the manuscript.
EMBARRASSING!!!
Grieving my first major grant proposal rejection with my first ever sub-30 5K run. Let's call it a tie!
What is more disappointing? Having a paper rejected from #NeurIPS or not being able to present a paper which you co-authored due to space constraints?
Subhankar Roy retweeted
I'm currently writing and editing ICLR submission (and yes, I'm a dinosaur. I still do this by hand, no AI, just a spell checker) and I realized that when I work on a paper, at every step I try to imagine how someone would read this. Is the information clear? Will they get the point? Do they need more information (or less)? This is how communication works ...
Subhankar Roy retweeted
Seems like this idea is starting to get traction (e.g. ICLR). But limits like 20 papers per author are still ridiculous. Let's make it 3--5.
Subhankar Roy retweeted
Two fully-funded PhDs at CRIL (CNRS / Université d'Artois, Lens co-supervised by me. Very different topics
Subhankar Roy retweeted
The variance across ICLR scores is wild, OpenAI should decrease the temperature
Subhankar Roy retweeted
🌺 Aloha! I will be presenting our work, "FedMVP: Federated Multimodal Visual Prompt Tuning for Vision-Language Models" at #ICCV2025 in Hawaii 🇺🇸 !
🗓️ Wednesday 22 October, Exhibit Hall I, Poster #1650, Session 4, 14:30 - 16:30 (HST)
@eliricci_ , @sroy907 , @BiplabB81293285
Having a paper, which was accepted by the AC, rejected by the PCs is really atrocious. This can damage the morale of young researchers, especially PhD students. Quota-based acceptance should be stated in the cfp so that the authors can calibrate their expectations. #neurips25
We submitted a paper on semantic segmentation to a CV conference that shall not be named.
Reviewer's comment, "The approach involves extracting high-quality domain knowledge from expert-written documents"
Dear reviewer, kindly choose a better LLM next time.
This year 11 researchers from University of Oxford have received ERC starting grants! To put things into perspective to those who don't know, an institute is fortunate to have just one accepted. Success rate is ~12%.
Congratulations to all the recipients.
Source: Outstanding early-career researchers awarded European Research Council funding to launch their ideas | University of Oxford share.google/Mx1m2tAVKNBLptB…
Subhankar Roy retweeted
The best research teams are not the ones with the most people, but the ones with the right people.
That should be a straight red for such a blatant dive inside the box
I find it weirdly unsettling that a human brain does what it does without
- backpropagating
- next token prediction
- denoising
- distributed training,
and does it a million times better than NNs. I wonder if we can ever figure out the dark sauce in "Intelligence" or "Evolution"
Any #NeurIPS2025 AC/SAC around who can clarify if in the Reviewer-AC discussion phase we reviewers are supposed to initiate discussion or wait for the AC to do so? For my batch the AC didn't post any message and idk if it's apt to initiate a discussion. Papers have mixed ratings.
