Oran Lang

Interdisciplinary expertise to advance human-centered explainable AI

Chloe R. Bennett, Heather Cole-Lewis, Stephanie Farquhar, Naama Haamel et autres

The field of artificial intelligence (AI) is rapidly influencing health and healthcare, but bias and inadequate subgroup performance persists. Previous work has clearly outlined the need for more rigorous attention to data representativeness and model performance to advance population health and reduce …

us (code pays fourni par la source)

Interdisciplinary Expertise to Advance Equitable Explainable AI

Chloe R. Bennett, Heather Cole-Lewis, Stephanie Farquhar, Naama Haamel et autres

The field of artificial intelligence (AI) is rapidly influencing health and healthcare, but bias and poor performance persists for populations who face widespread structural oppression. Previous work has clearly outlined the need for more rigorous attention to data representativeness and model performance …

Multi-turn Reinforcement Learning from Preference Human Feedback

Lior Shani, Aviv Rosenberg, Asaf Cassel, Oran Lang et autres

Reinforcement Learning from Human Feedback (RLHF) has become the standard approach for aligning Large Language Models (LLMs) with human preferences, allowing LLMs to demonstrate remarkable abilities in various tasks. Existing methods work by emulating the preferences at the single decision (turn) level, …

Using generative AI to investigate medical imagery models and datasets

Oran Lang, Doron Stupp, Ilana Traynis, Heather Cole-Lewis et autres

BACKGROUND: AI models have shown promise in performing many medical imaging tasks. However, our ability to explain what signals these models have learned is severely lacking. Explanations are needed in order to increase the trust of doctors in AI-based models, especially in …

us, il (code pays fourni par la source)

Multi-turn Reinforcement Learning with Preference Human Feedback

Lior Shani, Aviv Rosenberg, Asaf Cassel, Oran Lang et autres

Explaining counterfactual images

Oran Lang, Ilana Traynis, Yun Liu

us (code pays fourni par la source)

Gemini: A Family of Highly Capable Multimodal Models

Gemini Robotics Team, Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac et autres

This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding. The Gemini family consists of Ultra, Pro, and Nano sizes, suitable for applications ranging from complex reasoning tasks to on-device memory-constrained …

Using generative AI to investigate medical imagery models and datasets

Oran Lang, Doron Stupp, Ilana Traynis, Heather Cole-Lewis et autres

AI models have shown promise in many medical imaging tasks. However, our ability to explain what signals these models have learned is severely lacking. Explanations are needed in order to increase the trust in AI-based models, and could enable novel scientific discovery …

us (code pays fourni par la source)

The Hidden Language of Diffusion Models

Hila Chefer, Oran Lang, Mor Geva, Volodymyr Polosukhin et autres

Text-to-image diffusion models have demonstrated an unparalleled ability to generate high-quality, diverse images from a textual prompt. However, the internal representations learned by these models remain an enigma. In this work, we present Conceptor, a novel method to interpret the internal representation …

Imagic: Text-Based Real Image Editing with Diffusion Models

Bahjat Kawar, Shiran Zada, Oran Lang, Omer Tov et autres

Text-conditioned image editing has recently attracted considerable interest. However, most methods are currently limited to one of the following: specific editing types (e.g., object overlay, style transfer), synthetically generated images, or requiring multiple input images of a common object. In this paper …

us, il (code pays fourni par la source)

What You See is What You Read? Improving Text-Image Alignment Evaluation

Michal Yarom, Yonatan Bitton, Soravit Changpinyo, Roee Aharoni et autres

Automatically determining whether a text and a corresponding image are semantically aligned is a significant challenge for vision-language models, with applications in generative text-to-image and image-to-text tasks. In this work, we study methods for automatic text-image alignment evaluation. We first introduce SeeTRUE: …

What You See is What You Read? Improving Text-Image Alignment Evaluation

Michal Yarom, Yonatan Bitton, Soravit Changpinyo, Roee Aharoni et autres