58 citations · 120 across the 59 of their papers we have counts for
37 papers · 1 filter
Look Where You Say You're Looking: Self-Grounded Attention for Visual Reasoning
Uri Berger, Gal Chechik, Gal Dalal
We introduce Self-Saliency, a method for training Vision-Language Models (VLMs) to increase the alignment between their visual attention and the image regions mentioned in their re…
All modalities are equal, but video is more equal: Closing the Cross-Attention Gap in Joint Video Generation
Ohad Rahamim, Dvir Samuel, Idan Schwartz +1
Video is a rich representation of a physical event, capturing appearance, geometry, motion, and temporal evolution. Other modalities, such as 3D body motion or audio, encode narrow…
UniProbe: A Learnable Token-Level Hallucination Detector for Large VLMs using Multi-Structural Internal Representations
Dvir Samuel, Guy Bar-Shalom, Fabrizio Frasca +4
Large Vision-Language Models (LVLMs) achieve impressive visual reasoning and dialogue capabilities, yet frequently hallucinate content unsupported by the visual input. Effective mi…
Bootstrap Your Generator: Unpaired Visual Editing with Flow Matching
Yoad Tewel, Yuval Atzmon, Gal Chechik +1
Modern generative models possess a deep understanding of visual content, yet training them for image editing typically requires massive datasets of paired examples. This limits sca…
Fast 4D Mesh Generation by Spatio-Temporal Attention Chains
Dvir Samuel, Yuval Atzmon, Gal Chechik +1
4D mesh generation has recently emerged as a powerful paradigm for recovering dynamic 3D structure from videos, but existing methods remain slow, computationally expensive, and dif…
Compositional Video Generation via Inference-Time Guidance
Ariel Shaulov, Eitan Shaar, Amit Edenzon +2
Text-to-video diffusion models generate realistic videos, but often fail on prompts requiring fine-grained compositional understanding, such as relations between entities, attribut…
Latent Transfer Attack: Adversarial Examples via Generative Latent Spaces
Eitan Shaar, Ariel Shaulov, Yalcin Tur +2
Adversarial attacks are a central tool for probing the robustness of modern vision models, yet most methods optimize perturbations directly in pixel space under or $\…
Spanning the Visual Analogy Space with a Weight Basis of LoRAs
Hila Manor, Rinon Gal, Haggai Maron +2
Visual analogy learning enables image editing via demonstration rather than textual description, allowing users to specify complex transformations difficult to articulate in words.…
Fast Autoregressive Video Diffusion and World Models with Temporal Cache Compression and Sparse Attention
Dvir Samuel, Issar Tzachor, Matan Levy +3
Autoregressive video diffusion models enable streaming generation, opening the door to long-form synthesis, video world models, and interactive neural game engines. However, their…
Data-Driven Loss Functions for Inference-Time Optimization in Text-to-Image
Sapir Esther Yiflach, Yuval Atzmon, Gal Chechik
Text-to-image diffusion models can generate stunning visuals, yet they often fail at tasks children find trivial--like placing a dog to the right of a teddy bear rather than to the…
Per-Query Visual Concept Learning
Ori Malca, Dvir Samuel, Gal Chechik
Visual concept learning, also known as Text-to-image personalization, is the process of teaching new concepts to a pretrained model. This has numerous applications from product pla…
Policy Optimized Text-to-Image Pipeline Design
Uri Gadot, Rinon Gal, Yftah Ziser +2
Text-to-image generation has evolved beyond single monolithic models to complex multi-component pipelines. These combine fine-tuned generators, adapters, upscaling blocks and even…
Adapting to the Unknown: Training-Free Audio-Visual Event Perception with Dynamic Thresholds
Eitan Shaar, Ariel Shaulov, Gal Chechik +1
In the domain of audio-visual event perception, which focuses on the temporal localization and classification of events across distinct modalities (audio and visual), existing appr…
Single Image Iterative Subject-driven Generation and Editing
Yair Shpitzer, Gal Chechik, Idan Schwartz
Personalizing image generation and editing is particularly challenging when we only have a few images of the subject, or even a single image. A common approach to personalization i…
OmnimatteZero: Fast Training-free Omnimatte with Pre-trained Video Diffusion Models
Dvir Samuel, Matan Levy, Nir Darshan +2
In Omnimatte, one aims to decompose a given video into semantically meaningful layers, including the background and individual objects along with their associated effects, such as…
Bringing Objects to Life: training-free 4D generation from 3D objects through view consistent noise
Ohad Rahamim, Ori Malca, Dvir Samuel +1
Recent advancements in generative models have enabled the creation of dynamic 4D content - 3D objects in motion - based on text prompts, which holds potential for applications in v…
Motion by Queries: Identity-Motion Trade-offs in Text-to-Video Generation
Yuval Atzmon, Rinon Gal, Yoad Tewel +2
Text-to-video diffusion models have shown remarkable progress in generating coherent video clips from textual descriptions. However, the interplay between motion, structure, and id…
Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models
Yoad Tewel, Rinon Gal, Dvir Samuel +3
Adding Object into images based on text instructions is a challenging task in semantic image editing, requiring a balance between preserving the original scene and seamlessly integ…
ComfyGen: Prompt-Adaptive Workflows for Text-to-Image Generation
Rinon Gal, Adi Haviv, Yuval Alaluf +3
The practical use of text-to-image generation has evolved from simple, monolithic models to complex workflows that combine multiple specialized components. While workflow-based app…
IT: Idempotent Test-Time Training
Nikita Durasov, Assaf Shocher, Doruk Oner +3
Deep learning models often struggle when deployed in real-world settings due to distribution shifts between training and test data. While existing approaches like domain adaptation…
Make It Count: Text-to-Image Generation with an Accurate Number of Objects
Lital Binyamin, Yoad Tewel, Hilit Segev +3
Despite the unprecedented success of text-to-image diffusion models, controlling the number of depicted objects using text is surprisingly hard. This is important for various appli…
Lay-A-Scene: Personalized 3D Object Arrangement Using Text-to-Image Priors
Ohad Rahamim, Hilit Segev, Idan Achituve +3
Generating 3D visual scenes is at the forefront of visual generative AI, but current 3D generation techniques struggle with generating scenes with multiple high-resolution objects.…
DiffUHaul: A Training-Free Method for Object Dragging in Images
Omri Avrahami, Rinon Gal, Gal Chechik +4
Text-to-image diffusion models have proven effective for solving many image editing tasks. However, the seemingly straightforward task of seamlessly relocating objects within a sce…
Where's Waldo: Diffusion Features for Personalized Segmentation and Retrieval
Dvir Samuel, Rami Ben-Ari, Matan Levy +2
Personalized retrieval and segmentation aim to locate specific instances within a dataset based on an input image and a short description of the reference instance. While supervise…