riccardofosco.bsky.social
Sound effects, audio & video | PhD at @ISPAMM, @Sapienza | Former @C4DM, @QMUL
👤 Joined on 20 December 2024
46
Followers
130
Following
3
Total Posts
📜 Kullanıcı Geçmişi
- 20 Ara 2024, 12:58
🎉 Bluesky'e katıldı - İlk kullanıcı adı:
@riccardofosco.bsky.social
🚫 Blokladığı Kullanıcılar
❤️ Beğendiği Gönderiler
In Vision & Audio transformers, not all tokens need the same compute resources! We propose “modular learners” to control compute at token-level granularity (MHA & MLP): hard tokens get more, easy ones get less! w/ @sscardapane.bsky.social @neuralnoise.com @bartoszWojcik Soon #AAAI25 Link 👇
Show Post
Yet another pre-Christmas release!! 🎅🎄 Here is 𝐒𝐭𝐚𝐛𝐥𝐞-𝐕𝟐𝐀 which generates sound effects from silent video frames showing semantic and temporal alignment. 🎶🥁🎛️ Huge thanks to @riccardofosco.bsky.social Christian Marinoni and all co-authors 🤟
Show Post
I'm happy to have two papers accepted at #ICASSP2025! 1) Contrastive learning for audio-video sequences, exploiting the fact that they are *sequences*: arxiv.org/abs/2407.05782 2) Knowledge distillation at *pre-training* time to help generative speech enhancement: arxiv.org/abs/2409.09357
Show Post
Submissions are open for the IJCNN Special Track on "Human-AI Interaction in Creative Arts and Sciences". If you're a researcher or artist working on how AI intersects with human creativity and scientific inquiry, consider submitting a paper or demo: 2025.ijcnn.org/authors/spec...
Show Post