8 papers
Scene-VLM: Multimodal Video Scene Segmentation via Vision-Language Models
Nimrod Berman, Adam Botach, Emanuel Ben-Baruch +5
Segmenting long-form videos into semantically coherent scenes is a fundamental task in large-scale video understanding. Existing encoder-based methods are limited by visual-centric…
FreeSliders: Training-Free, Modality-Agnostic Concept Sliders for Fine-Grained Diffusion Control in Images, Audio, and Video
Rotem Ezra, Hedi Zisling, Nimrod Berman +5
Diffusion models have become state-of-the-art generative models for images, audio, and video, yet enabling fine-grained controllable generation, i.e., continuously steering specifi…
Disentanglement Beyond Static vs. Dynamic: A Benchmark and Evaluation Framework for Multi-Factor Sequential Representations
Tal Barami, Nimrod Berman, Ilan Naiman +3
Learning disentangled representations in sequential data is a key goal in deep learning, with broad applications in vision, audio, and time series. While real-world data involves m…
One-Step Offline Distillation of Diffusion-based Models via Koopman Modeling
Nimrod Berman, Ilan Naiman, Moshe Eliasof +2
Diffusion-based generative models have demonstrated exceptional performance, yet their iterative sampling procedures remain computationally expensive. A prominent strategy to mitig…
DiffSDA: Unsupervised Diffusion Sequential Disentanglement Across Modalities
Hedi Zisling, Ilan Naiman, Nimrod Berman +2
Unsupervised representation learning, particularly sequential disentanglement, aims to separate static and dynamic factors of variation in data without relying on labels. This rema…
LV-MAE: Learning Long Video Representations through Masked-Embedding Autoencoders
Ilan Naiman, Emanuel Ben-Baruch, Oron Anschel +4
In this work, we introduce long-video masked-embedding autoencoders (LV-MAE), a self-supervised learning framework for long video representation. Our approach treats short- and lon…