Guy Bar-Shalom

Hi! I am a Ph.D. Student in the Computer Science Department at the Technion under the joint supervision of Haggai Maron and Ran El-Yaniv . My research focuses on Geometric Deep Learning, leveraging data symmetries to enhance model learning. I explore applications in Graph Neural Networks and uncertainty estimation in both vision models and Large Language Models.

Previously (Summer 2022), I was a research scientist intern at Google-Verily working with Michael Elad on video analysis. In the summer of 2025, I was a research scientist intern at Meta.

Mail Scholar Github Twitter LinkedIn CV

Selected Publications

* indicates equal contribution

Neural Message-Passing on Attention Graphs for Hallucination Detection
Fabrizio Frasca*, Guy Bar-Shalom*, Yftah Ziser, Haggai Maron
arXiv.org, 2025

Beyond Next Token Probabilities: Learnable, Fast Detection of Hallucinations and Data Contamination on LLM Output Distributions (A shorter version also appeared in the Reliable and Responsible Foundation Models Workshop @ ICML 2025 as an oral presentation)
Guy Bar-Shalom*, Fabrizio Frasca*, Derek Lim, Yoav Gelberg, Yftah Ziser, Ran El-Yaniv, Gal Chechik, Haggai Maron
AAAI Conference on Artificial Intelligence (AAAI), 2026
Code

Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT
Guy Bar-Shalom*, Fabrizio Frasca*, Yaniv Galron, Yftah Ziser, Haggai Maron
Advances in Neural Information Processing Systems (NeurIPS), 2025
Code

Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity (Oral presentation)
Yam Eitan*, Yoav Gelberg*, Guy Bar-Shalom, Fabrizio Frasca, Michael Bronstein, Haggai Maron
International Conference on Learning Representations (ICLR), 2025
Code

A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening (A shorter version also appeared in the Symmetry and Geometry in Neural Representations Workshop @ NeurIPS 2024 winning the best paper award)
Guy Bar-Shalom*, Yam Eitan*, Fabrizio Frasca, Haggai Maron
Advances in Neural Information Processing Systems (NeurIPS), 2024
Poster / Code / Short talk

Subgraphormer: Unifying Subgraph GNNs and Graph Transformers via Graph Products
Guy Bar-Shalom, Beatrice Bevilacqua, Haggai Maron
International Conference on Machine Learning, (ICML), 2024
Poster / Code / Short talk / Slides

Weakly-supervised Representation Learning for Video Alignment and Analysis
Guy Bar-Shalom, George Leifman, Michael Elad
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024
Poster / Short talk

Window-Based Distribution Shift Detection for Deep Neural Networks
Guy Bar-Shalom, Yonatan Geifman, Ran El-Yaniv
Advances in Neural Information Processing Systems (NeurIPS), 2023
Poster / Code / Short talk

TransBoost: Improving the Best ImageNet Performance using Deep Transduction
Omer Belhasin*, Guy Bar-Shalom*, Ran El-Yaniv
Advances in Neural Information Processing Systems (NeurIPS), 2022
Poster / Code / Short talk

Based on Michael Niemeyer's website template.