8 papers
NAMESAKES: Probing Identity Memorization in Text-to-Image Models
Morris Alper, Vasudha Varadarajan, Moran Yanuka +2
Text-to-image (T2I) models generate realistic likenesses of some individuals when prompted with their names, raising privacy concerns. However, distinguishing whether a generated f…
ConlangCrafter: Constructing Languages with a Multi-Hop LLM Pipeline
Morris Alper, Moran Yanuka, Raja Giryes +1
Constructed languages (conlangs) such as Esperanto and Quenya have played diverse roles in art, philosophy, and international communication. Meanwhile, foundation models have revol…
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…
Principled Coarse-Grained Acceptance for Speculative Decoding in Speech
Moran Yanuka, Paul Dixon, Eyal Finkelshtein +2
Speculative decoding accelerates autoregressive speech generation by letting a fast draft model propose tokens that a larger target model verifies. However, for speech LLMs that ge…
ICC: Quantifying Image Caption Concreteness for Multimodal Dataset Curation
Moran Yanuka, Morris Alper, Hadar Averbuch-Elor +1
Web-scale training on paired text-image data is becoming increasingly central to multimodal learning, but is challenged by the highly noisy nature of datasets in the wild. Standard…
EditInspector: A Benchmark for Evaluation of Text-Guided Image Edits
Ron Yosef, Moran Yanuka, Yonatan Bitton +1
Text-guided image editing, fueled by recent advancements in generative AI, is becoming increasingly widespread. This trend highlights the need for a comprehensive framework to veri…