collaborators

6 papers

cs.CV2026

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…

cs.CV2026

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 $\…

cs.CV2026

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…

cs.CV2025

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…

cs.CV2025

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…

cs.CL2025

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…