Initialization using Update Approximation is a Silver Bullet for Extremely Efficient Low-Rank Fine-Tuningby Kaustubh Ponkshe,…
DreamBlend: Advancing Personalized Fine-tuning of Text-to-Image Diffusion Modelsby Shwetha Ram, Tal Neiman, Qianli Feng, Andrew…
On the effectiveness of discrete representations in sparse mixture of expertsby Giang Do, Kha Pham,…
Effective Fine-Tuning of Vision-Language Models for Accurate Galaxy Morphology Analysisby Ruoqi Wang, Haitao Wang, Qiong…
Enhancing Parameter-Efficient Fine-Tuning of Vision Transformers through Frequency-Based Adaptationby Son Thai Ly, Hien V. NguyenFirst…
All Seeds Are Not Equal: Enhancing Compositional Text-to-Image Generation with Reliable Random Seedsby Shuangqi Li,…
NeuroAI for AI Safetyby Patrick Mineault, Niccolò Zanichelli, Joanne Zichen Peng, Anton Arkhipov, Eli Bingham,…
Challenges in Adapting Multilingual LLMs to Low-Resource Languages using LoRA PEFT Tuningby Omkar Khade, Shruti…
Task Arithmetic Through The Lens Of One-Shot Federated Learningby Zhixu Tao, Ian Mason, Sanjeev Kulkarni,…
A gentle push funziona benissimo: making instructed models in Italian via contrastive activation steeringby Daniel…