Manvi Agarwal

Postdoc at Institut de l’Audition (Hearing Institute) | (re)tweets ∈ funny stuff ∪ science-y stuff

[Manvi Agarwal @ManviTweeteth]

@adilhossain @sharbat_c Thanks Adil da and hugs to Adelie

[Manvi Agarwal @ManviTweeteth]

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

[Manvi Agarwal @ManviTweeteth]

Jk it was super fun doing my PhD 😃

[Sharbatanu Chatterjee | শর্বতনু @sharbat_c]

The Wife is, from today, Dr. The Wife!

Very happy, congratulations @ManviTweeteth!

#PhDone

[Manvi Agarwal @ManviTweeteth]

@academicmargin @sharbat_c Thanks Indranil da !

[Manvi Agarwal @ManviTweeteth]

@mkhanpasha @sharbat_c Merci !! 👋 à Rasgulla Billa

[Manvi Agarwal @ManviTweeteth]

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

[Manvi Agarwal @ManviTweeteth]

@Freshwiz_Mafer @sharbat_c Thanks Mafer 💕

[Sharbatanu Chatterjee | শর্বতনু @sharbat_c]

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

https://t.co/jilf6Gbbgd

[Sharbatanu Chatterjee | শর্বতনু @sharbat_c]

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.

[Sharbatanu Chatterjee | শর্বতনু @sharbat_c]

Funny how this is true across countries.

[Sharbatanu Chatterjee | শর্বতনু @sharbat_c]

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.

[Manvi Agarwal @ManviTweeteth]

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.

[Manvi Agarwal @ManviTweeteth]

🚨 We just submitted a follow-up to this work, now available as a preprint: https://t.co/E0N3y4uQRp

[Manvi Agarwal @ManviTweeteth]

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 🧵

[Manvi Agarwal @ManviTweeteth]

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.

[Manvi Agarwal @ManviTweeteth]

With these two interventions, we obtain better performance at lower cost! 🚀
Curious? Check out the companion webpage: https://t.co/GniiGQl56F

[Manvi Agarwal @ManviTweeteth]

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 🧵

[Manvi Agarwal @ManviTweeteth]

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.