1 citations · 1 across the 5 of their papers we have counts for
9 papers
Cross-Prompt Inference Mitigates Rare-Class Suppression in Imbalanced VLM Finetuning
Emanuel Ben Baruch, Sivan Biham, Alon Shoshan +2
When a vision-language model is finetuned on class-imbalanced data, rare-class recall can fall well below the model's own zero-shot performance. In this regime, we uncover a surpri…
Group-Aware Reinforcement Learning for Output Diversity in Large Language Models
Oron Anschel, Alon Shoshan, Adam Botach +7
Large Language Models (LLMs) often suffer from mode collapse, repeatedly generating the same few completions even when many valid answers exist, limiting their diversity across a w…
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…
FPGAN-Control: A Controllable Fingerprint Generator for Training with Synthetic Data
Alon Shoshan, Nadav Bhonker, Emanuel Ben Baruch +5
Training fingerprint recognition models using synthetic data has recently gained increased attention in the biometric community as it alleviates the dependency on sensitive persona…
Asymmetric Image Retrieval with Cross Model Compatible Ensembles
Ori Linial, Alon Shoshan, Nadav Bhonker +4
The asymmetrical retrieval setting is a well suited solution for resource constrained applications such as face recognition and image retrieval. In this setting, a large model is u…
Synthetic Data for Model Selection
Alon Shoshan, Nadav Bhonker, Igor Kviatkovsky +2
Recent breakthroughs in synthetic data generation approaches made it possible to produce highly photorealistic images which are hardly distinguishable from real ones. Furthermore,…
GAN-Control: Explicitly Controllable GANs
Alon Shoshan, Nadav Bhonker, Igor Kviatkovsky +1
We present a framework for training GANs with explicit control over generated images. We are able to control the generated image by settings exact attributes such as age, pose, exp…
Adversarial Feedback Loop
Firas Shama, Roey Mechrez, Alon Shoshan +1
Thanks to their remarkable generative capabilities, GANs have gained great popularity, and are used abundantly in state-of-the-art methods and applications. In a GAN based model, a…
Dynamic-Net: Tuning the Objective Without Re-training for Synthesis Tasks
Alon Shoshan, Roey Mechrez, Lihi Zelnik-Manor
One of the key ingredients for successful optimization of modern CNNs is identifying a suitable objective. To date, the objective is fixed a-priori at training time, and any variat…