Postdoc at Institut de l’Audition (Hearing Institute) | (re)tweets ∈ funny stuff ∪ science-y stuff
Joined December 2015
- Tweets 299
- Following 348
- Followers 216
- Likes 1,075
44 Photos and videos
Manvi Agarwal retweeted
Mar 15
Hehehe enough offense/defense, time to log off and read. Thanks to @sharbat_c for the books 😻
2
2
267
Mar 15
The Wife is, from today, Dr. The Wife!
Very happy, congratulations @ManviTweeteth!
#PhDone
1
1
7
289
Manvi Agarwal retweeted
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
1
4
13
6,591
Manvi Agarwal retweeted
6 Nov 2025
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.
1
1
2
622
Manvi Agarwal retweeted
26 Apr 2025
Funny how this is true across countries.
2
1
645
Manvi Agarwal retweeted
18 Apr 2025
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.
18 Apr 2025
Ici en France, la recherche est une priorité, l’innovation une culture, la science un horizon sans limite. Chercheurs, chercheuses du monde entier, choisissez la France, choisissez l’Europe ! Je vous donne rendez-vous le 5 mai.
→ choosefrance.fr/forscience
1
1
4
700
8 Apr 2025
🚨 We just submitted a follow-up to this work, now available as a preprint: hal.science/hal-05021809
7 Apr 2025
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 🧵
1
1
2
402
8 Apr 2025
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.
1
1
195
8 Apr 2025
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.
2
162
7 Apr 2025
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 🧵
1
1
5
943
7 Apr 2025
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.
1
1
123
7 Apr 2025
With these two interventions, we obtain better performance at lower cost! 🚀
Curious? Check out the companion webpage: bit.ly/faststructurepe
1
104
Manvi Agarwal retweeted
27 Jan 2025
Did Qin Shi Huang know when he united China under a Legalist bureaucratic system 2200 years ago, that he would start a process that would end up in me filling out forms in triplicate from Calcutta to Paris, instead of doing science?
FML.
1
2
267
Manvi Agarwal retweeted
16 Dec 2024
Just explained to general disbelief of my Indian parents how @Sorbonne_Univ_ hasn't yet reimbursed me ~1200€ for over 4 years, & that I will not be paid my December salary in time due to bureacratic incompetence.
They thought such incompetence was just an Indian particularity!
1
1
5
494
28 Nov 2024
I will be in London next week visiting @c4dm ! If you’re around, come say hi 😄
In other news, we’re looking for a Master’s student to carry forward some of this work that I’ll be talking about at next week’s seminar 👇(advert in following tweet)
28 Nov 2024
Next Tuesday, 3/12 at 2pm, we will host a seminar by Manvi Agarwal @ManviTweeteth on 'Fast Structure-informed Positional Encoding for Music Generation'.
More info at:
c4dm.eecs.qmul.ac.uk/news/20…
1
1
7
643