Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Guy

Guy

16 indexed papers

Recent (6 mo)
13
With code
0
Influential cites
0
Benchmarked
0

Publications per year

16
26

Top categories

AI×9ML×7NLP×3Crypto×3Audio and Speech Processing×2Logic×2Multimedia×1Sound×1

Frequent co-authors

Guy Van den Broeck4×
Heng Zhao2×
Zilei Shao2×
Zhe Zeng2×
Meihua Dang2×
Linxin Song2×

Research Timeline

2026
SALLIE: Safeguarding Against Latent Language & Image Exploits

SALLIE introduces a lightweight, modal-agnostic runtime detection framework that effectively safeguards LLMs and VLMs against both textual and visual jailbreaks and prompt injections without performance degradation.

SL5 Standard for AI Security

The paper introduces Security Level 5 (SL5), a new, highly stringent security standard for AI systems designed to withstand attacks from state-level, top-tier cyber adversaries.

Agent Security is a Systems Problem

The paper argues that agent security must be treated as a systems problem, requiring the enforcement of security invariants at the system level rather than solely relying on improving the underlying AI model's robustness.

Neural Network Verification using Partial Multi-Neuron Relaxation

The paper introduces partial multi-neuron relaxation, a novel verification technique that selectively computes tight linear bounds for a small subset of neurons to improve the efficiency and tightness of neural network safety verification.

Neural Network Verification using Partial Multi-Neuron Relaxation

The paper introduces partial multi-neuron relaxation, a novel verification technique that selectively computes tight linear bounds for a small subset of neurons to improve the efficiency and tightness of neural network safety verification.

ProbMoE: Differentiable Probabilistic Routing for Mixture-of-Experts

The paper introduces ProbMoE, a probabilistic routing framework that tackles the non-differentiability of top-$k$ routing in Mixture-of-Experts (MoE) models, achieving strong performance with improved expert utilization.

Mitigating Bias in Locally Constrained Decoding via Tractable Proposals

The paper proposes a novel probabilistic globally constrained decoding (P-GCD) method that efficiently constructs proposals for locally constrained decoding, significantly improving convergence speed and performance compared to existing approaches.

ProbMoE: Differentiable Probabilistic Routing for Mixture-of-Experts

The paper introduces ProbMoE, a probabilistic routing framework that tackles the non-differentiability of top-$k$ routing in Mixture-of-Experts (MoE) models, achieving strong performance with improved expert utilization.

Mitigating Bias in Locally Constrained Decoding via Tractable Proposals

The paper proposes a novel probabilistic globally constrained decoding (P-GCD) method that efficiently constructs proposals for locally constrained decoding, significantly improving convergence speed and performance compared to existing approaches.

Integrating national forest inventory, airborne lidar, and satellite imagery for wall-to-wall mapping of forest structure with computer vision

The authors introduce the VibrantForests framework for mapping forest attributes and providing a foundation for effective forest and wildfire planning.

Interpretable Human-Label-Free Deep Learning for Real-Bogus Classification with Uncertainty Quantification

This paper proposes a Real-Bogus classification framework using injection-driven, weakly supervised training without human-labeled data, achieving strong performance and calibrated uncertainties.

Multimodal Digital Biomarker for Asthma: Complementary Roles of Vocal, Clinical and Demographic Factors

A multimodal Mixture-of-Experts framework was developed for asthma detection using vocal biomarkers and clinical data, achieving better performance than unimodal and bimodal approaches.

Online Learning via Learned Latent Bayesian Tracking

This paper proposes AURA, a meta-learning framework for efficient online adaptation of high-dimensional models in non-stationary environments.

Dream to Assist: Intent-Conditioned World Models for Shared Vehicle Control

The paper presents a model-based reinforcement learning framework for assistive agents in shared-control settings that addresses the challenges of proactive assistance and human legibility.

Incongruence-Aware Evaluation of Multimodal Speech Emotion Recognition in Audio Large Language Models

This paper investigates the impact of incongruence between text and audio on speech emotion recognition in voice-interactive large language models.

MaxIM: Maximally Informative Incremental Summarization via Reinforcement Learning

The paper introduces MaxIM, a framework for incremental summarization that optimizes memory representation for downstream task utility.

Highlighted terms show continued research focus across papers

Papers

cs.AIcs.LGEmpiricalRecentNov 9, 2026

MaxIM: Maximally Informative Incremental Summarization via Reinforcement Learning

Jihwan Jeong, Guy Tennenholtz, Yinlam Chow, Chih-Wei Hsu +1 more

The paper introduces MaxIM, a framework for incremental summarization that optimizes memory representation for downstream task utility.

View →
cs.AIcs.CLcs.MMEmpirical
Recent
Oct 29, 2026

Incongruence-Aware Evaluation of Multimodal Speech Emotion Recognition in Audio Large Language Models

Fengji Jing, Guy Laban

This paper investigates the impact of incongruence between text and audio on speech emotion recognition in voice-interactive large language models.

View →
cs.ROcs.HCcs.LGEmpiricalRecentOct 26, 2026

Dream to Assist: Intent-Conditioned World Models for Shared Vehicle Control

Jonathan DeCastro, Thomas Balch, Emily Sumner, Deepak Gopinath +8 more

The paper presents a model-based reinforcement learning framework for assistive agents in shared-control settings that addresses the challenges of proactive assistance and human legibility.

View →
cs.LGeess.SPEmpiricalRecentSep 25, 2026

Online Learning via Learned Latent Bayesian Tracking

Guy Gerson, Tomer Raviv, Nir Shlezinger, Tirza Routtenberg +1 more

This paper proposes AURA, a meta-learning framework for efficient online adaptation of high-dimensional models in non-stationary environments.

View →
eess.ASEmpiricalRecentJul 9, 2026

Multimodal Digital Biomarker for Asthma: Complementary Roles of Vocal, Clinical and Demographic Factors

Vladimir Despotovic, Milena Despotovic, Abir Elbeji, Petr V. Nazarov +1 more

A multimodal Mixture-of-Experts framework was developed for asthma detection using vocal biomarkers and clinical data, achieving better performance than unimodal and bimodal approaches.

View →
astro-ph.IMastro-ph.GAastro-ph.HEEmpiricalRecentJul 6, 2026

Interpretable Human-Label-Free Deep Learning for Real-Bogus Classification with Uncertainty Quantification

Raphaël Bonnet-Guerrini, Bruno Sanchez, Dominique Fouchez, Benjamin Racine +4 more

This paper proposes a Real-Bogus classification framework using injection-driven, weakly supervised training without human-labeled data, achieving strong performance and calibrated uncertainties.

View →
cs.LGcs.CVEmpiricalRecentJun 18, 2026

Integrating national forest inventory, airborne lidar, and satellite imagery for wall-to-wall mapping of forest structure with computer vision

Luke J. Zachmann, David D. Diaz, Vincent A. Landau, Chelsey Walden-Schreiner +7 more

The authors introduce the VibrantForests framework for mapping forest attributes and providing a foundation for effective forest and wildfire planning.

View →
cs.LGcs.AIRecentJun 1, 2026

ProbMoE: Differentiable Probabilistic Routing for Mixture-of-Experts

Heng Zhao, Zilei Shao, Guy Van den Broeck, Zhe Zeng

The paper introduces ProbMoE, a probabilistic routing framework that tackles the non-differentiability of top-$k$ routing in Mixture-of-Experts (MoE) models, achieving strong performance with improved…

View →
cs.CLRecentJun 1, 2026

Mitigating Bias in Locally Constrained Decoding via Tractable Proposals

Meihua Dang, Linxin Song, Honghua Zhang, Jieyu Zhao +2 more

The paper proposes a novel probabilistic globally constrained decoding (P-GCD) method that efficiently constructs proposals for locally constrained decoding, significantly improving convergence speed…

View →
cs.LGcs.AIRecentJun 1, 2026

ProbMoE: Differentiable Probabilistic Routing for Mixture-of-Experts

Heng Zhao, Zilei Shao, Guy Van den Broeck, Zhe Zeng

The paper introduces ProbMoE, a probabilistic routing framework that tackles the non-differentiability of top-$k$ routing in Mixture-of-Experts (MoE) models, achieving strong performance with improved…

View →
cs.CLRecentJun 1, 2026

Mitigating Bias in Locally Constrained Decoding via Tractable Proposals

Meihua Dang, Linxin Song, Honghua Zhang, Jieyu Zhao +2 more

The paper proposes a novel probabilistic globally constrained decoding (P-GCD) method that efficiently constructs proposals for locally constrained decoding, significantly improving convergence speed…

View →
cs.LOcs.AIRecentMay 28, 2026

Neural Network Verification using Partial Multi-Neuron Relaxation

Ido Shmuel, Guy Katz

The paper introduces partial multi-neuron relaxation, a novel verification technique that selectively computes tight linear bounds for a small subset of neurons to improve the efficiency and tightness…

View →
cs.LOcs.AIRecentMay 28, 2026

Neural Network Verification using Partial Multi-Neuron Relaxation

Ido Shmuel, Guy Katz

The paper introduces partial multi-neuron relaxation, a novel verification technique that selectively computes tight linear bounds for a small subset of neurons to improve the efficiency and tightness…

View →
cs.CRcs.AIMay 18, 2026

Agent Security is a Systems Problem

Mihai Christodorescu, Earlence Fernandes, Ashish Hooda, Somesh Jha +10 more

The paper argues that agent security must be treated as a systems problem, requiring the enforcement of security invariants at the system level rather than solely relying on improving the underlying A…

View →
cs.CRMay 8, 2026

SL5 Standard for AI Security

Lisa Thiergart, Yoav Tzfati, Peter Wagstaff, Guy +2 more

The paper introduces Security Level 5 (SL5), a new, highly stringent security standard for AI systems designed to withstand attacks from state-level, top-tier cyber adversaries.

View →
cs.CRcs.AIApr 6, 2026

SALLIE: Safeguarding Against Latent Language & Image Exploits

Guy Azov, Ofer Rivlin, Guy Shtar

SALLIE introduces a lightweight, modal-agnostic runtime detection framework that effectively safeguards LLMs and VLMs against both textual and visual jailbreaks and prompt injections without performan…

View →