18 papers
Analysis-by-Proxy: Localization Signals in VLMs Operating as Condition Encoders
Yoav Baron, Sara Dorfman, Roni Paiss +2
Vision-Language Models (VLMs) are increasingly utilized as the conditioning backbone for diffusion-based image editing due to their remarkable multimodal reasoning capabilities. Wh…
Token-to-Token Alignment of Text Embeddings for Semantic Blending
Saar Huberman, Ron Mokady, Or Patashnik +1
In modern generative models, images are specified and controlled through text prompts. In practice, images are generated from sequences of tokens derived from these prompts. Howeve…
Keep The Essentials: Efficient Reference Conditioned Generation via Token Dropping
Rishubh Parihar, Ayush Raina, R. Venkatesh Babu +1
Reference-based diffusion models enable highly controllable image generation by leveraging elements from input images to guide prompt-driven synthesis. However, these models are co…
Semantic Browsing: Controllable Diversity for Image Generation
Sara Dorfman, Maya Vishnevsky, Omer Dahary +2
Modern text-to-image models excel in visual fidelity and prompt adherence. However, this strict adherence comes at the cost of diversity: generated samples tend to collapse into a…
Reference-Driven Multi-Speaker Audio Scene Generation from In-the-Wild Priors
Michael Finkelson, Daniel Segal, Eitan Richardson +7
Existing multi-speaker dialogue systems bind speakers to utterances through structured supervision: per-turn tags, multi-stream transcriptions, or learnable speaker embeddings. The…
JUST-DUB-IT: Video Dubbing via Joint Audio-Visual Diffusion
Anthony Chen, Naomi Ken Korem, Gal Zeevi +6
Audio-Visual Foundation Models, which are pretrained to jointly generate sound and visual content, have recently shown an unprecedented ability to model multi-modal generation and…