472 citations · 624 across the 37 of their papers we have counts for
43 papers
Stuck on Shuffle: On Attribute-Object Binding in Vision-Language Models
Netanel Y. Tamir, Michael Green, Issar Tzachor +4
Retrieval is a fundamental task in multimodal systems: given an image or text query, the goal is to find the most relevant images or texts in a collection, often using a shared emb…
Learning to Read the Contextual Tokens in Diffusion Transformers
Omer Dahary, Etai Sella, Hadar Averbuch-Elor +2
Multimodal Diffusion Transformers (MM-DiTs) jointly process visual and textual representations throughout generation. These models repeatedly update the text tokens through multimo…
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…
Prox-E: Fine-Grained 3D Shape Editing via Primitive-Based Abstractions
Etai Sella, Hao Phung, Nitay Amiel +3
Text-based 2D image editing models have recently reached an impressive level of maturity, motivating a growing body of work that heavily depends on these models to drive 3D edits.…
ParetoSlider: Diffusion Models Post-Training for Continuous Reward Control
Shelly Golan, Michael Finkelson, Ariel Bereslavsky +2
Reinforcement Learning (RL) post-training has become the standard for aligning generative models with human preferences, yet most methods rely on a single scalar reward. When multi…
HDR Video Generation via Latent Alignment with Logarithmic Encoding
Naomi Ken Korem, Mohamed Oumoumad, Harel Cain +8
High dynamic range (HDR) imagery offers a rich and faithful representation of scene radiance, but remains challenging for generative models due to its mismatch with the bounded, pe…
Untwisting RoPE: Frequency Control for Shared Attention in DiTs
Aryan Mikaeili, Or Patashnik, Andrea Tagliasacchi +2
Positional encodings are essential to transformer-based generative models, yet their behavior in multimodal and attention-sharing settings is not fully understood. In this work, we…
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…
LooseRoPE: Content-aware Attention Manipulation for Semantic Harmonization
Etai Sella, Yoav Baron, Hadar Averbuch-Elor +2
Recent diffusion-based image editing methods commonly rely on text or high-level instructions to guide the generation process, offering intuitive but coarse control. In contrast, w…
VLM-Guided Adaptive Negative Prompting for Creative Generation
Shelly Golan, Yotam Nitzan, Zongze Wu +1
Creative generation is the synthesis of new, surprising, and valuable samples that reflect user intent yet cannot be envisioned in advance. This task aims to extend human imaginati…
Visual Diffusion Models are Geometric Solvers
Nir Goren, Shai Yehezkel, Omer Dahary +3
In this paper we show that visual diffusion models can serve as effective geometric solvers: they can directly reason about geometric problems by working in pixel space. We first d…
Object-level Visual Prompts for Compositional Image Generation
Gaurav Parmar, Or Patashnik, Kuan-Chieh Wang +5
We introduce a method for composing object-level visual prompts within a text-to-image diffusion model. Our approach addresses the task of generating semantically coherent composit…
Nested Attention: Semantic-aware Attention Values for Concept Personalization
Or Patashnik, Rinon Gal, Daniil Ostashev +3
Personalizing text-to-image models to generate images of specific subjects across diverse scenes and styles is a rapidly advancing field. Current approaches often face challenges i…
Sharp-It: A Multi-view to Multi-view Diffusion Model for 3D Synthesis and Manipulation
Yiftach Edelstein, Or Patashnik, Dana Cohen-Bar +1
Advancements in text-to-image diffusion models have led to significant progress in fast 3D content creation. One common approach is to generate a set of multi-view images of an obj…
Omni-ID: Holistic Identity Representation Designed for Generative Tasks
Guocheng Qian, Kuan-Chieh Wang, Or Patashnik +5
We introduce Omni-ID, a novel facial representation designed specifically for generative tasks. Omni-ID encodes holistic information about an individual's appearance across diverse…
Stable Flow: Vital Layers for Training-Free Image Editing
Omri Avrahami, Or Patashnik, Ohad Fried +4
Diffusion models have revolutionized the field of content synthesis and editing. Recent models have replaced the traditional UNet architecture with the Diffusion Transformer (DiT),…
MaterialFusion: Enhancing Inverse Rendering with Material Diffusion Priors
Yehonathan Litman, Or Patashnik, Kangle Deng +4
Recent works in inverse rendering have shown promise in using multi-view images of an object to recover shape, albedo, and materials. However, the recovered components often fail t…
TurboEdit: Text-Based Image Editing Using Few-Step Diffusion Models
Gilad Deutch, Rinon Gal, Daniel Garibi +2
Diffusion models have opened the path to a wide range of text-based image editing frameworks. However, these typically build on the multi-step nature of the diffusion backwards pro…
LCM-Lookahead for Encoder-based Text-to-Image Personalization
Rinon Gal, Or Lichter, Elad Richardson +4
Recent advancements in diffusion models have introduced fast sampling methods that can effectively produce high-quality images in just one or a few denoising steps. Interestingly,…
Be Yourself: Bounded Attention for Multi-Subject Text-to-Image Generation
Omer Dahary, Or Patashnik, Kfir Aberman +1
Text-to-image diffusion models have an unprecedented ability to generate diverse and high-quality images. However, they often struggle to faithfully capture the intended semantics…