6 papers
TokenTrim: Inference-Time Token Pruning for Autoregressive Long Video Generation
Ariel Shaulov, Eitan Shaar, Amit Edenzon +1
Auto-regressive video generation enables long video synthesis by iteratively conditioning each new batch of frames on previously generated content. However, recent work has shown t…
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…
Classifier-Guided Captioning Across Modalities
Ariel Shaulov, Tal Shaharabany, Eitan Shaar +2
Most current captioning systems use language models trained on data from specific settings, such as image-based captioning via Amazon Mechanical Turk, limiting their ability to gen…
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…
Detection-Driven Object Count Optimization for Text-to-Image Diffusion Models
Oz Zafar, Yuval Cohen, Lior Wolf +1
Accurately controlling object count in text-to-image generation remains a key challenge. Supervised methods often fail, as training data rarely covers all count variations. Methods…
Training-Free Consistent Text-to-Image Generation
Yoad Tewel, Omri Kaduri, Rinon Gal +4
Text-to-image models offer a new level of creative flexibility by allowing users to guide the image generation process through natural language. However, using these models to cons…