Shie Mannor
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Shie Mannor has a total of 58 co-authors. Here are the top co-authors by number of shared publications:
- Uri Alon
Dept. Molecular Cell Biology, Weizmann Institute of Science, Rehovot, Israel
3 shared publications - Chen Tessler
NVIDIA, Santa Clara, USA
2 shared publications Constantine Caramanis
Department of Electrical and Computer Engineering The University of Texas at Austin USA
2 shared publications- Huan Xu
Department of Electrical and Computer Engineering McGill University Canada
2 shared publications - Itay Naeh
Rafael -Advanced Defense Systems Ltd Israel
2 shared publications Jonathan Somer
2 shared publications
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 7899-7910
Hierarchical Adversarial Bandits for Online Configuration Optimization
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 7899-7910
Open AccessHierarchical Adversarial Bandits for Online Configuration Optimization
- Top Cited PapersOpen Access
- 21 January 2026
- Published by Springer Nature in Nature
- Vol. 650 (8101) , 490-499
Temporal tissue dynamics from a spatial snapshot
Physiological and pathological processes such as inflammation and cancer emerge from interactions between cells over time1. However, methods to follow cell populations over time within the native context of a human tissue are lacking because a biopsy offers only a single snapshot. Here we present one-shot tissue dynamics reconstruction (OSDR), an approach to estimate a dynamical model of cell populations based on a single tissue sample. OSDR uses spatial proteomics to learn how the composition of cellular neighbourhoods influences division rate, providing a dynamical model of cell population change over time. We apply OSDR to human breast cancer data2,3,4, and reconstruct two fixed points of fibroblasts and macrophage interactions5,6. These fixed points correspond to hot and cold fibrosis7, in agreement with co-culture experiments that measured these dynamics directly8. We then use OSDR to discover a pulse-generating excitable circuit of T and B cells in the tumour microenvironment, suggesting temporal flares of anticancer immune responses. Finally, we study longitudinal biopsies from a triple-negative breast cancer clinical trial3, in which OSDR predicts the collapse of the tumour cell population in responders but not in non-responders, based on early-treatment biopsies. OSDR can be applied to a wide range of spatial proteomics assays to enable analysis of tissue dynamics based on patient biopsies.
- 21 January 2026
- Published by Springer Nature in Nature
- Vol. 650 (8101) , 490-499
Top Cited PapersOpen AccessTemporal tissue dynamics from a spatial snapshot
Physiological and pathological processes such as inflammation and cancer emerge from interactions between cells over time1. However, methods to follow cell populations over time within the native context of a human tissue are lacking because a biopsy offers only a single snapshot. Here we present one-shot tissue dynamics reconstruction (OSDR), an approach to estimate a dynamical model of cell populations based on a single tissue sample. OSDR uses spatial proteomics to learn how the composition of cellular neighbourhoods influences division rate, providing a dynamical model of cell population change over time. We apply OSDR to human breast cancer data2,3,4, and reconstruct two fixed points of fibroblasts and macrophage interactions5,6. These fixed points correspond to hot and cold fibrosis7, in agreement with co-culture experiments that measured these dynamics directly8. We then use OSDR to discover a pulse-generating excitable circuit of T and B cells in the tumour microenvironment, suggesting temporal flares of anticancer immune responses. Finally, we study longitudinal biopsies from a triple-negative breast cancer clinical trial3, in which OSDR predicts the collapse of the tumour cell population in responders but not in non-responders, based on early-treatment biopsies. OSDR can be applied to a wide range of spatial proteomics assays to enable analysis of tissue dynamics based on patient biopsies.
- Open Access
OSDR2.0 infers microenvironment-driven cell-state transitions and population dynamics from a single spatial biopsy
Cell populations in human tissues change over time by cell division, death and transitions between functional states. In the tumor microenvironment (TME), such dynamics are central to immune evasion, stromal remodeling and therapeutic response. However, it is difficult to measure such dynamics in vivo because usually only a single biopsy is available providing a static snapshot. To obtain cell population dynamics from a snapshot we previously developed One Shot Dynamic Reconstruction (OSDR1.0), an algorithm that reconstructs cell population dynamics over weeks to months from a spatial biopsy using cell-type information and a proliferation marker. OSDR1.0 however does not include transitions between cell states. Here we present OSDR2.0, an extension that incorporates transitions between cell states inferred from the local cellular neighborhood. The algorithm OSDR2.0 models the probability of a cell being in a given state (e.g., PD1 + vs. PD1 − T cell, or cancer-associated vs. resting fibroblast) as a function of its surrounding cell types. These state-transition rules are then integrated into simulations of population dynamics. After the cell population is advanced by a timestep, the cell states are adjusted according to the new neighborhoods, using the fact that cell state transitions, which take hours, are typically much more rapid than cell population changes on the scale of weeks, and can thus be considered at quasi-steady-state. Applying OSDR2.0 to spatial proteomics data from triple-negative breast cancer (TNBC), we find that cell state is strongly associated with local microenvironment composition. Incorporating state transitions significantly improves the ability to predict treatment response - OSDR2.0 accurately separates responders from nonresponders to chemotherapy and immunotherapy based on early post-treatment biopsies, outperforming OSDR1.0 that does not include cell state transitions. This work highlights the importance of cell state plasticity in shaping tumor response and opens a way to infer both population dynamics and cell state transitions from static clinical samples.
Open AccessOSDR2.0 infers microenvironment-driven cell-state transitions and population dynamics from a single spatial biopsy
Cell populations in human tissues change over time by cell division, death and transitions between functional states. In the tumor microenvironment (TME), such dynamics are central to immune evasion, stromal remodeling and therapeutic response. However, it is difficult to measure such dynamics in vivo because usually only a single biopsy is available providing a static snapshot. To obtain cell population dynamics from a snapshot we previously developed One Shot Dynamic Reconstruction (OSDR1.0), an algorithm that reconstructs cell population dynamics over weeks to months from a spatial biopsy using cell-type information and a proliferation marker. OSDR1.0 however does not include transitions between cell states. Here we present OSDR2.0, an extension that incorporates transitions between cell states inferred from the local cellular neighborhood. The algorithm OSDR2.0 models the probability of a cell being in a given state (e.g., PD1 + vs. PD1 − T cell, or cancer-associated vs. resting fibroblast) as a function of its surrounding cell types. These state-transition rules are then integrated into simulations of population dynamics. After the cell population is advanced by a timestep, the cell states are adjusted according to the new neighborhoods, using the fact that cell state transitions, which take hours, are typically much more rapid than cell population changes on the scale of weeks, and can thus be considered at quasi-steady-state. Applying OSDR2.0 to spatial proteomics data from triple-negative breast cancer (TNBC), we find that cell state is strongly associated with local microenvironment composition. Incorporating state transitions significantly improves the ability to predict treatment response - OSDR2.0 accurately separates responders from nonresponders to chemotherapy and immunotherapy based on early post-treatment biopsies, outperforming OSDR1.0 that does not include cell state transitions. This work highlights the importance of cell state plasticity in shaping tumor response and opens a way to infer both population dynamics and cell state transitions from static clinical samples.
- 6 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 6 (1) , 159-168
An Improved and Explainable Electricity Price Forecasting Model via SHAP-Based Error Compensation Approach
Forecasting errors in power markets, even as small as 1%, can have significant financial implications. However, even high-performance artificial intelligence (AI) based electricity price forecasting (EPF) models have instances when their prediction error is much higher than those shown by mean performance metrics. To date, explainable AI has been used to enhance the model transparency and trustworthiness of AI-based EPF models. However, this paper demonstrates that insights from explainable AI (XAI) techniques can be expanded beyond its primary task of explanatory visualizations. This work presents a XAI-based error compensation approach to improve model performance and identify irregular predictions. The first phase of the proposed approach involves error quantification through a Shapley additive explanations (SHAP) based corrector model that fine-tunes the base predictor’s forecasts. Using this corrector model’s SHAP explanations, the proposed approach distinguishes high-accuracy predictions from lower ones in the second stage. Additionally, these explanations are more simplified than the base model, making them easier for non-expert users like bidding agents. Performance enhancement and insightful user-centric explanations are crucial for real-world scenarios like price spikes during network congestion, high renewable penetration, and fluctuating fuel costs. Case studies discussed here show the efficacy of the proposed approach independent of model architecture, feature combination, or behavioral patterns of electricity prices in different markets.
- 6 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 6 (1) , 159-168
An Improved and Explainable Electricity Price Forecasting Model via SHAP-Based Error Compensation Approach
Forecasting errors in power markets, even as small as 1%, can have significant financial implications. However, even high-performance artificial intelligence (AI) based electricity price forecasting (EPF) models have instances when their prediction error is much higher than those shown by mean performance metrics. To date, explainable AI has been used to enhance the model transparency and trustworthiness of AI-based EPF models. However, this paper demonstrates that insights from explainable AI (XAI) techniques can be expanded beyond its primary task of explanatory visualizations. This work presents a XAI-based error compensation approach to improve model performance and identify irregular predictions. The first phase of the proposed approach involves error quantification through a Shapley additive explanations (SHAP) based corrector model that fine-tunes the base predictor’s forecasts. Using this corrector model’s SHAP explanations, the proposed approach distinguishes high-accuracy predictions from lower ones in the second stage. Additionally, these explanations are more simplified than the base model, making them easier for non-expert users like bidding agents. Performance enhancement and insightful user-centric explanations are crucial for real-world scenarios like price spikes during network congestion, high renewable penetration, and fluctuating fuel costs. Case studies discussed here show the efficacy of the proposed approach independent of model architecture, feature combination, or behavioral patterns of electricity prices in different markets.
- Open Access
Temporal tissue dynamics from a spatial snapshot
Physiological and pathological processes such as inflammation or cancer emerge from the interactions between cells over time. However, methods to follow cell populations over time within the native context of a human tissue are lacking, because a biopsy offers only a single snapshot. Here we present one-shot tissue dynamics reconstruction (OSDR), an approach to estimate a dynamical model of cell populations based on a single tissue sample. OSDR uses spatial proteomics to learn how the composition of cellular neighborhoods influences division rate, providing a dynamical model of cell population change over time. We apply OSDR to human breast cancer data, and reconstruct two fixed points of fibroblasts and macrophage interactions. These fixed points correspond to hot and cold fibrosis, in agreement with co-culture experiments that measured these dynamics directly. We then use OSDR to discover a pulse-generating excitable circuit of T and B cells in the tumor microenvironment, suggesting temporal flares of adaptive anti-cancer responses. Finally, we study longitudinal biopsies from a triple negative breast cancer clinical trial, where OSDR predicts the collapse of the tumor cell population in responders versus non-responders based on early treatment biopsies. OSDR can be applied to a wide range of spatial proteomics assays to enable analysis of tissue dynamics based on patient biopsies.
Open AccessTemporal tissue dynamics from a spatial snapshot
Physiological and pathological processes such as inflammation or cancer emerge from the interactions between cells over time. However, methods to follow cell populations over time within the native context of a human tissue are lacking, because a biopsy offers only a single snapshot. Here we present one-shot tissue dynamics reconstruction (OSDR), an approach to estimate a dynamical model of cell populations based on a single tissue sample. OSDR uses spatial proteomics to learn how the composition of cellular neighborhoods influences division rate, providing a dynamical model of cell population change over time. We apply OSDR to human breast cancer data, and reconstruct two fixed points of fibroblasts and macrophage interactions. These fixed points correspond to hot and cold fibrosis, in agreement with co-culture experiments that measured these dynamics directly. We then use OSDR to discover a pulse-generating excitable circuit of T and B cells in the tumor microenvironment, suggesting temporal flares of adaptive anti-cancer responses. Finally, we study longitudinal biopsies from a triple negative breast cancer clinical trial, where OSDR predicts the collapse of the tumor cell population in responders versus non-responders based on early treatment biopsies. OSDR can be applied to a wide range of spatial proteomics assays to enable analysis of tissue dynamics based on patient biopsies.
- Open Access
- 23 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-9
CALM: Conditional Adversarial Latent Models for Directable Virtual Characters
In this work, we present Conditional Adversarial Latent Models (CALM), an approach for generating diverse and directable behaviors for user-controlled interactive virtual characters. Using imitation learning, CALM learns a representation of movement that captures the complexity and diversity of human motion, and enables direct control over character movements. The approach jointly learns a control policy and a motion encoder that reconstructs key characteristics of a given motion without merely replicating it. The results show that CALM learns a semantic motion representation, enabling control over the generated motions and style-conditioning for higher-level task training. Once trained, the character can be controlled using intuitive interfaces, akin to those found in video games.
- 23 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Open AccessCALM: Conditional Adversarial Latent Models for Directable Virtual Characters
In this work, we present Conditional Adversarial Latent Models (CALM), an approach for generating diverse and directable behaviors for user-controlled interactive virtual characters. Using imitation learning, CALM learns a representation of movement that captures the complexity and diversity of human motion, and enables direct control over character movements. The approach jointly learns a control policy and a motion encoder that reconstructs key characteristics of a given motion without merely replicating it. The results show that CALM learns a semantic motion representation, enabling control over the generated motions and style-conditioning for higher-level task training. Once trained, the character can be controlled using intuitive interfaces, akin to those found in video games.
- Open Access
Twice Regularized Markov Decision Processes: The Equivalence between Robustness and Regularization
Robust Markov decision processes (MDPs) aim to handle changing or partially known system dynamics. To solve them, one typically resorts to robust optimization methods. However, this significantly increases computational complexity and limits scalability in both learning and planning. On the other hand, regularized MDPs show more stability in policy learning without impairing time complexity. Yet, they generally do not encompass uncertainty in the model dynamics. In this work, we aim to learn robust MDPs using regularization. We first show that regularized MDPs are a particular instance of robust MDPs with uncertain reward. We thus establish that policy iteration on reward-robust MDPs can have the same time complexity as on regularized MDPs. We further extend this relationship to MDPs with uncertain transitions: this leads to a regularization term with an additional dependence on the value function. We then generalize regularized MDPs to twice regularized MDPs ($\text{R}^2$ MDPs), i.e., MDPs with $\textit{both}$ value and policy regularization. The corresponding Bellman operators enable us to derive planning and learning schemes with convergence and generalization guarantees, thus reducing robustness to regularization. We numerically show this two-fold advantage on tabular and physical domains, highlighting the fact that $\text{R}^2$ preserves its efficacy in continuous environments.Open AccessTwice Regularized Markov Decision Processes: The Equivalence between Robustness and Regularization
Robust Markov decision processes (MDPs) aim to handle changing or partially known system dynamics. To solve them, one typically resorts to robust optimization methods. However, this significantly increases computational complexity and limits scalability in both learning and planning. On the other hand, regularized MDPs show more stability in policy learning without impairing time complexity. Yet, they generally do not encompass uncertainty in the model dynamics. In this work, we aim to learn robust MDPs using regularization. We first show that regularized MDPs are a particular instance of robust MDPs with uncertain reward. We thus establish that policy iteration on reward-robust MDPs can have the same time complexity as on regularized MDPs. We further extend this relationship to MDPs with uncertain transitions: this leads to a regularization term with an additional dependence on the value function. We then generalize regularized MDPs to twice regularized MDPs ($\text{R}^2$ MDPs), i.e., MDPs with $\textit{both}$ value and policy regularization. The corresponding Bellman operators enable us to derive planning and learning schemes with convergence and generalization guarantees, thus reducing robustness to regularization. We numerically show this two-fold advantage on tabular and physical domains, highlighting the fact that $\text{R}^2$ preserves its efficacy in continuous environments. - Open Access
Twice regularized MDPs and the equivalence between robustness and regularization
Robust Markov decision processes (MDPs) aim to handle changing or partially known system dynamics. To solve them, one typically resorts to robust optimization methods. However, this significantly increases computational complexity and limits scalability in both learning and planning. On the other hand, regularized MDPs show more stability in policy learning without impairing time complexity. Yet, they generally do not encompass uncertainty in the model dynamics. In this work, we aim to learn robust MDPs using regularization. We first show that regularized MDPs are a particular instance of robust MDPs with uncertain reward. We thus establish that policy iteration on reward-robust MDPs can have the same time complexity as on regularized MDPs. We further extend this relationship to MDPs with uncertain transitions: this leads to a regularization term with an additional dependence on the value function. We finally generalize regularized MDPs to twice regularized MDPs (R${}^2$ MDPs), i.e., MDPs with $\textit{both}$ value and policy regularization. The corresponding Bellman operators enable developing policy iteration schemes with convergence and robustness guarantees. It also reduces planning and learning in robust MDPs to regularized MDPs.Open AccessTwice regularized MDPs and the equivalence between robustness and regularization
Robust Markov decision processes (MDPs) aim to handle changing or partially known system dynamics. To solve them, one typically resorts to robust optimization methods. However, this significantly increases computational complexity and limits scalability in both learning and planning. On the other hand, regularized MDPs show more stability in policy learning without impairing time complexity. Yet, they generally do not encompass uncertainty in the model dynamics. In this work, we aim to learn robust MDPs using regularization. We first show that regularized MDPs are a particular instance of robust MDPs with uncertain reward. We thus establish that policy iteration on reward-robust MDPs can have the same time complexity as on regularized MDPs. We further extend this relationship to MDPs with uncertain transitions: this leads to a regularization term with an additional dependence on the value function. We finally generalize regularized MDPs to twice regularized MDPs (R${}^2$ MDPs), i.e., MDPs with $\textit{both}$ value and policy regularization. The corresponding Bellman operators enable developing policy iteration schemes with convergence and robustness guarantees. It also reduces planning and learning in robust MDPs to regularized MDPs. - Open Access
Over-the-Air Adversarial Flickering Attacks against Video Recognition Networks
Deep neural networks for video classification, just like image classification networks, may be subjected to adversarial manipulation. The main difference between image classifiers and video classifiers is that the latter usually use temporal information contained within the video. In this work we present a manipulation scheme for fooling video classifiers by introducing a flickering temporal perturbation that in some cases may be unnoticeable by human observers and is implementable in the real world. After demonstrating the manipulation of action classification of single videos, we generalize the procedure to make universal adversarial perturbation, achieving high fooling ratio. In addition, we generalize the universal perturbation and produce a temporal-invariant perturbation, which can be applied to the video without synchronizing the perturbation to the input. The attack was implemented on several target models and the transferability of the attack was demonstrated. These properties allow us to bridge the gap between simulated environment and real-world application, as will be demonstrated in this paper for the first time for an over-the-air flickering attack.
Open AccessOver-the-Air Adversarial Flickering Attacks against Video Recognition Networks
Deep neural networks for video classification, just like image classification networks, may be subjected to adversarial manipulation. The main difference between image classifiers and video classifiers is that the latter usually use temporal information contained within the video. In this work we present a manipulation scheme for fooling video classifiers by introducing a flickering temporal perturbation that in some cases may be unnoticeable by human observers and is implementable in the real world. After demonstrating the manipulation of action classification of single videos, we generalize the procedure to make universal adversarial perturbation, achieving high fooling ratio. In addition, we generalize the universal perturbation and produce a temporal-invariant perturbation, which can be applied to the video without synchronizing the perturbation to the input. The attack was implemented on several target models and the transferability of the attack was demonstrated. These properties allow us to bridge the gap between simulated environment and real-world application, as will be demonstrated in this paper for the first time for an over-the-air flickering attack.
- Open Access
Stealing Black-Box Functionality Using The Deep Neural Tree Architecture
This paper makes a substantial step towards cloning the functionality of black-box models by introducing a Machine learning (ML) architecture named Deep Neural Trees (DNTs). This new architecture can learn to separate different tasks of the black-box model, and clone its task-specific behavior. We propose to train the DNT using an active learning algorithm to obtain faster and more sample-efficient training. In contrast to prior work, we study a complex "victim" black-box model based solely on input-output interactions, while at the same time the attacker and the victim model may have completely different internal architectures. The attacker is a ML based algorithm whereas the victim is a generally unknown module, such as a multi-purpose digital chip, complex analog circuit, mechanical system, software logic or a hybrid of these. The trained DNT module not only can function as the attacked module, but also provides some level of explainability to the cloned model due to the tree-like nature of the proposed architecture.
Open AccessStealing Black-Box Functionality Using The Deep Neural Tree Architecture
This paper makes a substantial step towards cloning the functionality of black-box models by introducing a Machine learning (ML) architecture named Deep Neural Trees (DNTs). This new architecture can learn to separate different tasks of the black-box model, and clone its task-specific behavior. We propose to train the DNT using an active learning algorithm to obtain faster and more sample-efficient training. In contrast to prior work, we study a complex "victim" black-box model based solely on input-output interactions, while at the same time the attacker and the victim model may have completely different internal architectures. The attacker is a ML based algorithm whereas the victim is a generally unknown module, such as a multi-purpose digital chip, complex analog circuit, mechanical system, software logic or a hybrid of these. The trained DNT module not only can function as the attacked module, but also provides some level of explainability to the cloned model due to the tree-like nature of the proposed architecture.