Shashank Agnihotri

Improving Feature Stability during Upsampling -- Spectral Artifacts and the Importance of Spatial Context, Accepted at @eccvconf 2024, a joint work with @JuliaGrabinski and @margret_keuper. Affiliations: @dwsunima @FraunhoferITWM @cvml_mpiinf @KeuperLabs

@sidgairo18 Bada socho

@shashankska Sure, but I was referring more to the reviewer form and scores - to be uniform / calibrated across venues.

Food for thought - 🤔 I've been thinking about this long and hard - having been reviewing for popular ML / CV conferences (ICML, ICLR, NeurIPS, CVPR, ICCV, ECCV) - with the community submitting papers across these, it only makes sense to have a uniform reviewer form, guidelines, rules and format across these conferences. Personally I have a real hard time calibrating my scale from 1-10 (ICLR) to 1-6 for CVPR, then we comes ICML which also has 1-6 but 3,4 are weak reject/accept instead of 3,4 as borderline reject/accept (for CVPR). This only gets trickier and worse when you add ICCV, ECCV, NeurIPS into the mix. Then, you add NLP related conferences and Robotics ones, to make the entire system more and more confusing - with uncalibrated reviewer scores coming - which may or may not truly reflect the reviewer's intentions. Happy to hear the thoughts of others. cc: @icmlconf @CVPR @NeurIPSConf @iclr_conf @ICCVConference @eccvconf

@sidgairo18 Rolling reviews covers that!

@PaulGavrikov @icmlconf The ICML files.....

@icmlconf Release their names

To ensure compliance w peer-review policies, ICML has removed 795 reviews (1% of total) by reviewers who used LLMs when they explicitly agreed to not. Consequently, 497 papers (2% of all submissions) of these (reciprocal) reviewers have been desk rejected Details in blog post 👇

Why I'm pro the oxford comma 😂🤣

@PaulGavrikov @grok @gork

@shashankska @grok @gork answer the human!

Help, I hit my Claude limit. What do I do now?????

sidgairo18.github.io/how_to_review_… Since people are now on their final stretch of finalising their ICML reviews. Here are some resources that I had compiled (it's an abridged version of the ICML 2022 reviewer guidelines and some additional resources). Pretty neat 😉 Remember - review as if you would want your paper to be reviewed, read, understood and critiqued.

@PaulGavrikov @grok @grok, would you answer any stupid thing a paid user asks?

@shashankska @grok explain to him why clankers are absolutely essential these days

@sidgairo18 Bade log!

Splitting the G of a Guinness 🍻

@sidgairo18 I know right! This bot @sidgairo18 keeps posting every 2-3 hours about something random!

Boy these Twitter (X) bots are really irksome 😡💢

@sidgairo18 Bade log! Talks and all🙌🏽

🍰Recently gave a talk at our MPI-INF, D2 seminar about DAVE. Find the slides (pdf) here: sidgairo18.github.io/ppts/dave_ppt.…

@PaulGavrikov Amazing research always gets recognised!

@shashankska Thanks 🙏

2/2 accepted at CVPR!

@PaulGavrikov Damn!!!

#CVPR2026 has 156 accepted workshops 🤯

@sidgairo18 Why are you removing space in “mm” and not “em”?!

This tiny innocent looking command, has saved more lives than anyone can probably imagine. Give it a Nobel Peace prize already! 😉🏅

Currently underway in Peridot 202 #AAAI2026 Singapore Expo at the AIR-FM workshop!

The keynotes at the AIR-FM Workshop are currently underway! Join us in Peridot 202 for the some interesting talks on Reliability of LLMs and VLMs in the Real World! #AAAI2026 @aaai #VLMs #LLMs #Hallucinations #Reliability #RealWorld

@PaulGavrikov @sidgairo18 And the people making up papers and citations using LLMs which get accepted to NeurIPS 2025 and the Program Chairs that simply let that go!

@sidgairo18 Said the first year PhD student before submitting to his first conference

Research and writing papers is fun 🤓

Now that phantom citations hallucinated by LLMs have been found in NeurIPS papers, what is to be done? Develop a software tool that authors are expected to run to verify their references in Google Scholar. Next, conferences use it to screen papers, and desk reject violators.