Donato Crisostomi ✈️ NeurIPS
@crisostomi.bsky.social
🧑🎓 PhD stud. @ Sapienza, Rome
🥷stealth-mode CEO
🔬prev visiting @ Cambridge | RS intern @ Amazon Search | RS intern @ Alexa.
🆓 time 🎭improv theater, 🤿scuba diving, ⛰️hiking
🥷stealth-mode CEO
🔬prev visiting @ Cambridge | RS intern @ Amazon Search | RS intern @ Alexa.
🆓 time 🎭improv theater, 🤿scuba diving, ⛰️hiking
By orthogonalizing the (low-rank approximated) task singular vectors, we effectively eliminate interference.
This leads to an impressive +15% gain without any test-time adaptation!
The improvement is consistent across all datasets.
🧵(5/6)
This leads to an impressive +15% gain without any test-time adaptation!
The improvement is consistent across all datasets.
🧵(5/6)
January 8, 2025 at 7:00 PM
By orthogonalizing the (low-rank approximated) task singular vectors, we effectively eliminate interference.
This leads to an impressive +15% gain without any test-time adaptation!
The improvement is consistent across all datasets.
🧵(5/6)
This leads to an impressive +15% gain without any test-time adaptation!
The improvement is consistent across all datasets.
🧵(5/6)
📢Prepend “Singular” to “Task Vectors” and get +15% average accuracy for free!
1. Perform a low-rank approximation of layer-wise task vectors.
2. Minimize task interference by orthogonalizing inter-task singular vectors.
🧵(1/6)
1. Perform a low-rank approximation of layer-wise task vectors.
2. Minimize task interference by orthogonalizing inter-task singular vectors.
🧵(1/6)
January 8, 2025 at 7:00 PM
📢Prepend “Singular” to “Task Vectors” and get +15% average accuracy for free!
1. Perform a low-rank approximation of layer-wise task vectors.
2. Minimize task interference by orthogonalizing inter-task singular vectors.
🧵(1/6)
1. Perform a low-rank approximation of layer-wise task vectors.
2. Minimize task interference by orthogonalizing inter-task singular vectors.
🧵(1/6)