Manvi Agarwal

@adilhossain @sharbat_c Thanks Adil da and hugs to Adelie

@sharbat_c @ManviTweeteth Anek anek shubhechha Dr madam ke !

The Wife is, from today, Dr. The Wife! Very happy, congratulations @ManviTweeteth! #PhDone

@neel_kolhe @sharbat_c @xkcd Hehehe enough offense/defense, time to log off and read. Thanks to @sharbat_c for the books 😻

Jk it was super fun doing my PhD 😃

@academicmargin @sharbat_c Thanks Indranil da !

@sharbat_c @ManviTweeteth Congratulations!

@mkhanpasha @sharbat_c Merci !! 👋 à Rasgulla Billa

@sharbat_c @ManviTweeteth Félicitations à la Docteure la Wife 🧿🌸✊🏼

@sharbat_c @ManviTweeteth @ManviTweeteth yesterday embodied the famous @xkcd panel!

@Freshwiz_Mafer @sharbat_c Thanks Mafer 💕

@sharbat_c @ManviTweeteth Bravo!!! Well deserved!!!!

Do you want to do a PhD on exploring brain-body interactions with expansion microscopy at the Paris-Saclay Institute of Neuroscience, through the Marie-Curie COFUND program? Apply! Deadline : 23 February 2026 Supervisor : Tihana JOVANIC lightinparis.eu

It should be obvious to French commentators that both the following facts are true : (1) a Zohran Mamdani could not be elected in France because of the lower acceptance and integration of minorities and (2) his economic agenda is pretty normal and not at all radical for France.

Funny how this is true across countries.

Monsieur le Président, j’ai Choosé France for Science (France m’a Choosé for Science, merci MSCA fellowship) et ça passe bien (there are many amazing laboratoires dans ce pays) but sans mesures concrètes pour améliorer la bureaucratie scientifique, il est inutile d'en parler.

3️⃣ We explain why structural information in PE has proven to be empirically successful.  We go back to 1️⃣ and use the content-context connection to show that the higher is the mutual information between data and its positional representation, the better is task performance.

2️⃣ We introduce a new positional encoding method - RoPEPool - that can model causality. How does RoPEPool compare to RoPE and F-StrIPE? Our analysis with a toy example says: RoPEPool isn’t just different, it’s also richer in terms of expressivity.

🚨 We just submitted a follow-up to this work, now available as a preprint: hal.science/hal-05021809

With these two interventions, we obtain better performance at lower cost! 🚀 Curious? Check out the companion webpage: bit.ly/faststructurepe

In our paper, we show that stochastic positional encoding is, in fact, a noisy version of a well-known kernel approximation technique: Random Fourier Features. We also show how prior knowledge (e.g. related to musical structure) can be used in such linear-complexity Transformers.

ICASSP 2025 has begun! I will be presenting "F-StrIPE: Fast Structure-Informed Positional Encoding for Symbolic Music Generation" on April 11 in the lecture session "Machine learning for speech, audio and music processing II" at 2 PM. More details below 🧵