39 citations · 39 across the 2 of their papers we have counts for
3 papers
cs.SD2026
ID-LoRA: Identity-Driven Audio-Video Personalization with In-Context LoRA
Aviad Dahan, Moran Yanuka, Noa Kraicer +2
Existing video personalization methods preserve visual likeness but treat video and audio separately. Without access to the visual scene, audio models cannot synchronize sounds wit…
cs.CV2025
LiteAttention: A Temporal Sparse Attention for Diffusion Transformers
Dor Shmilovich, Tony Wu, Aviad Dahan +1
Diffusion Transformers, particularly for video generation, achieve remarkable quality but suffer from quadratic attention complexity, leading to prohibitive latency. Existing accel…
cs.CV2023★ 39 cited
AutoSAM: Adapting SAM to Medical Images by Overloading the Prompt Encoder
Tal Shaharabany, Aviad Dahan, Raja Giryes +1
The recently introduced Segment Anything Model (SAM) combines a clever architecture and large quantities of training data to obtain remarkable image segmentation capabilities. Howe…