1. X
  2. Emanuele Rossi
Log inSign up
Emanuele Rossi
508 posts
Emanuele Rossi profile banner
user avatar

Emanuele Rossi

@emaros96
PostDoc in MLxAnimal Communication @GladiaLab in @SapienzaRoma. Previously, PhD in Graph ML @twitter and @imperialcollege.
emanuelerossi.co.uk
Joined December 2015
703
Following
5,356
Followers
RepliesRepliesMediaMedia
  • user avatar
    Emanuele Rossi
    @emaros96
    May 28
    Can a sentence carry a sound? In Communicating Sound Through Natural Language, we introduce lexical acoustic coding (LAC): a way for LLM agents to transmit short sounds as structured English, then re-render the same audio back from that text. (1/6)
    Image
    00:00
  • user avatar
    Emanuele Rossi
    @emaros96
    May 19
    The Lightning Network makes Bitcoin payments faster and cheaper, but forced closures remain a major challenge: they reduce reliability and lock up capital. Check out our new work with @sntonelli and @ambosstech on predicting forced closures in the Lightning Network ⚡️
    user avatar
    AMBOSS ⚡
    @ambosstech
    May 19
    Force closures on the Lightning Network = locked capital for weeks + degraded reliability. Can we predict them using only public gossip? We built a 2-year LN benchmark and tested everything from MLPs to temporal GNNs. (1/5) 🧵👇
    Image
  • user avatar
    Emanuele Rossi
    @emaros96
    Apr 2
    +1 for Animal Language Processing as a name for the field, and really like the focus on cross-species methods and most of all using ML for hypothesis-generation
    This post is unavailable.
  • user avatar
    Emanuele Rossi
    @emaros96
    Jan 5
    Great opportunity to work on automating AI agents for scientific discovery with extremely talented and fun people!
    user avatar
    Emanuele Rodolà
    @EmanueleRodola
    Jan 5
    looking for postdocs @embl + @SapienzaRoma want to work on Agents for Discovery? @Fabio_Petroni and I are looking for candidates to co-advise under an EIPOD-LinC fellowship. let's build cool tools that AI x Scientists would actually use! apply by feb: shorturl.at/WRwbD
    Image
  • user avatar
    Emanuele Rossi
    @emaros96
    Nov 19, 2025
    To move towards decoding animal communication, we need models that can understand any species, any acoustic pattern, with any prompt. Our new work shows how model merging can make bioacoustics foundation models more robust and generalizable, a key step toward that goal 🦜🐋
    user avatar
    GLADIA Research Lab
    @GladiaLab
    Nov 19, 2025
    Model merging restores instruction following in bioacoustics foundation models, setting a new SOTA in zero shot unseen species classification arxiv.org/abs/2511.05171 📍Spotlight at NeurIPS MLxAnimalComm 🤝 @DMarincione @DonatoCrisosto1 @robdessi @EmanueleRodola @emaros96 (1/6)
    Image

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Advertisement
Advertisement