Integrated Calendar

The development of high energy density, long running rechargeable batteries like
Li ion batteries, that power so successfully all mobile electronic devices, can be
considered as the greatest success of modern electrochemistry.
However, the basis for this success was the capability of exploring most complex
electrodes, electrolyte solutions and reactive interfaces by most sophisticated
electroanalytical tools in conjunction with advanced spectroscopic and microscopic
was a first-rate leader in electroanalytical ז"ל techniques. Professor Israel Rubinstein
chemistry. I learned a lot from him.
The main theme of this presentation is to examine what is the true horizons for advanced
high energy density batteries that can promote the electro-mobility revolution. The
limiting factor in Li-ion batteries in terms of energy density, cost, potential, durability
and cycling efficiency are the cathode materials used. We will examine most energetic
cathode materials and novel approaches we developed for their stabilization. We
describe in this lecture which electrode materials can be relevant, methodologies
of their stabilization by doping, coating, and affecting electrodes surface chemistry
by the use of active additives. Most important cathode materials are comprising the
5 elements Li,Ni,Co,Mn,O at different stoichiometries that determine voltage and
specific capacities. We will explain how the stoichiometry dictates basic cathodes
properties.1,2 We will discuss the renaissance of Li metal-based rechargeable batteries.3
We have learned how the stabilize Li metal anodes in rechargeable batteries using
reactive electrolyte solutions that induce excellent passivation through controlled
surface reactions. The emphasis is on fluorinated co-solvents that open the door for a
very rich surface chemistry that forms passivating surface films that behave as ideal
solid electrolyte interphase on both anodes and cathodes in advanced secondary Li
batteries. This field provides fascinating examples how systematic basic scientific
work leads to development of most practical devices for energy storage & conversion.

The rapid growth of generative models allows an ever-increasing variety of capabilities. Yet, these models may also produce undesired content such as unsafe images, private information, or copyrighted material.

In this talk, I will discuss practical methods to prevent undesired generations. First, I will show how the challenge of avoiding undesired generations manifested itself in a simple Capture-the-Flag LLM setting, where even our top defense strategy was breached. Next, I will demonstrate a similar vulnerability in state-of-the-art concept erasure methods for Text-to-Image models. Finally, I will describe the notion of ‘Unconditional Concept Erasure’ aiming to mitigate such vulnerabilities. I will show that Task Vectors can achieve Unconditional Concept Erasure, and discuss the challenge of applying Task Vectors in practice.

Bio: Niv is a postdoctoral researcher at New York University hosted by Prof. Chinmay Hegde. He received a BSc in mathematics with physics as part of the Technion Excellence Program. He received his PhD in computer science from the Hebrew University of Jerusalem, advised by Prof. Yedid Hoshen. Niv was awarded the Israeli data science scholarship for outstanding postdoctoral fellows (VATAT). He is interested in anomaly detection, model personalization, and AI safety for Vision

Text-to-image (T2I) diffusion/flow models achieve state-of-the-art results in image synthesis. Many works leverage these models for real image editing, where a predominant approach involves inverting the image into its corresponding gaussian-like noise map. However, inversion by itself is often insufficient for structure preserving edits. In our first work in this talk, termed ‘An Edit Friendly DDPM Noise Space’ [1], we present alternative latent noise maps for denoising diffusion probabilistic models (DDPMs) that do not have a standard normal distribution. These noise maps allow for perfect reconstruction of any real image, and lead to structure preserving edits, as we exemplify in our experiments.
In our second work, we tackle the task of text-based video editing using T2I diffusion models. Here the main challenge lies in maintaining the temporal consistency of the original video during the edit. Many methods leverage explicit correspondence mechanisms, which struggle with strong nonrigid motion. In contrast, our method termed ‘Slicedit’ [2], introduces a fundamentally different approach, which is based on the observation that spatiotemporal slices of natural videos exhibit similar characteristics to natural images. Thus, the same T2I diffusion model that is normally used only as a prior on video frames, can also serve as a strong prior for enhancing temporal consistency by applying it on spatiotemporal slices. As we show Sliceditgenerates videos that retain the structure and motion of the original video without relying on explicit correspondence matching while adhering to the target text. Finally, in our most recent work, we will discuss ‘FlowEdit’ [3], a novel text-based image editing method that leverages the increasingly popular flow models without relying on inversion. Our method constructs an ODE that directly maps between the source and target distributions (corresponding to the source and target text prompts) and achieves a lower transport cost than the inversion approach. This leads to state-of-the-art results, as we illustrate with Stable Diffusion 3 and FLUX.

[1] An Edit Friendly DDPM Noise Space: Inversion and Manipulations - CVPR24’  https://arxiv.org/abs/2304.06140

[2] Slicedit: Zero-Shot Video Editing With Text-to-Image Diffusion Models Using Spatio-Temporal Slices - ICML24’ https://arxiv.org/abs/2405.12211

[3] FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models – under review https://arxiv.org/abs/2412.08629

Bio: Vladimir Kulikov, PhD student at the Technion, under the supervision of Prof. Tomer Michaeli. Currently studying Deep Generative Models with emphasis on Computer Vision.