6 papers
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 $\…
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…
FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation
Ariel Shaulov, Itay Hazan, Lior Wolf +1
Text-to-video diffusion models are notoriously limited in their ability to model temporal aspects such as motion, physics, and dynamic interactions. Existing approaches address thi…
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…