Reposted by Ville Hautamäki
🧵 ICASSP 2026 update: two papers involving StatML members have been accepted. 🎉
One on targeted fine tuning for DNN based wireless receivers using influence functions, and one on generalizable speech deepfake detection via meta learned LoRA.
Huge congratulations to all authors! 🙌
One on targeted fine tuning for DNN based wireless receivers using influence functions, and one on generalizable speech deepfake detection via meta learned LoRA.
Huge congratulations to all authors! 🙌
January 27, 2026 at 4:18 PM
🧵 ICASSP 2026 update: two papers involving StatML members have been accepted. 🎉
One on targeted fine tuning for DNN based wireless receivers using influence functions, and one on generalizable speech deepfake detection via meta learned LoRA.
Huge congratulations to all authors! 🙌
One on targeted fine tuning for DNN based wireless receivers using influence functions, and one on generalizable speech deepfake detection via meta learned LoRA.
Huge congratulations to all authors! 🙌
Federico presenting our poster in NeurIPS 2025
December 4, 2025 at 2:28 AM
Federico presenting our poster in NeurIPS 2025
Janne Laakkonen presenting our work at AI-DOC seminar.
November 14, 2025 at 12:53 PM
Janne Laakkonen presenting our work at AI-DOC seminar.
Awesome to meet other AI researchers and enthusiasts in Aalto University.
November 13, 2025 at 11:09 AM
Awesome to meet other AI researchers and enthusiasts in Aalto University.
Reposted by Ville Hautamäki
Our paper “Zero-shot World Models via Search in Memory” (by F. Malato & @villeh.bsky.social) was accepted to #NeurIPS2025! 🎉 A training-free world model predicting dynamics via memory search.
Poster: Exhibit Hall C,D,E on Wed 3 Dec 4:30–7:30 PM PST 🔗 arxiv.org/abs/2510.16123
See you in San Diego!
Poster: Exhibit Hall C,D,E on Wed 3 Dec 4:30–7:30 PM PST 🔗 arxiv.org/abs/2510.16123
See you in San Diego!
Zero-shot World Models via Search in Memory
World Models have vastly permeated the field of Reinforcement Learning. Their ability to model the transition dynamics of an environment have greatly improved sample efficiency in online RL. Among the...
arxiv.org
October 29, 2025 at 1:20 PM
Our paper “Zero-shot World Models via Search in Memory” (by F. Malato & @villeh.bsky.social) was accepted to #NeurIPS2025! 🎉 A training-free world model predicting dynamics via memory search.
Poster: Exhibit Hall C,D,E on Wed 3 Dec 4:30–7:30 PM PST 🔗 arxiv.org/abs/2510.16123
See you in San Diego!
Poster: Exhibit Hall C,D,E on Wed 3 Dec 4:30–7:30 PM PST 🔗 arxiv.org/abs/2510.16123
See you in San Diego!