firstbacksecondback
340 Results
|
Workshop
|
Jogging the Memory of Unlearned LLMs Through Targeted Relearning Attacks Shengyuan Hu · Yiwei Fu · Steven Wu · Virginia Smith |
||
|
Workshop
|
Dynamic Vocabulary Pruning in Early-Exit LLMs · Karim Abdel Sadek · Joan Velja · Matteo Nulli · Metod Jazbec |
||
|
Poster
|
Thu 16:30 |
Is Programming by Example Solved by LLMs? Wen-Ding Li · Kevin Ellis |
|
|
Workshop
|
LLMs Infer Protected Attributes Beyond Proxy Features Dimitri Staufer |