News & Events

News

Here are 31 articles from Tech.AI PIs that will be presented at NeurIPS 2024 in Vancouver, Canada:

• Zero-to-Hero: Enhancing Zero-Shot Novel View Synthesis via Attention Map Filtering Authors: Ido Sobol, Chenfeng Xu, Or Litany

NeurIPS Poster Zero-to-Hero: Enhancing Zero-Shot Novel View Synthesis via Attention Map Filtering

• A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening Authors: Guy Bar-Shalom, Yam Eitan, Fabrizio Frasca, Haggai Maron

NeurIPS Poster A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening

• GRANOLA: Adaptive Normalization for Graph Neural Networks Authors: Moshe Eliasof, Beatrice Bevilacqua, Carola-Bibiane Schönlieb, Haggai Maron

NeurIPS Poster GRANOLA: Adaptive Normalization for Graph Neural Networks

• Fast Encoder-Based 3D from Casual Videos via Point Track Processing Authors: Yoni Kasten, Wuyue Lu, Haggai Maron

NeurIPS Poster Fast Encoder-Based 3D from Casual Videos via Point Track Processing

• The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof Authors: Derek Lim, Theo Putterman, Robin Walters, Haggai Maron, Stefanie Jegelka

NeurIPS Poster The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof

• Image-aware Evaluation of Generated Medical Reports Authors: Gefen Dawidowicz, Elad Hirsch, Ayellet Tal

NeurIPS Poster Image-aware Evaluation of Generated Medical Reports

• Sequential Signal Mixing Aggregation for Message Passing Graph Neural Networks Authors: Mitchell Keren Taraday, Almog David, Chaim Baskin

NeurIPS Poster Sequential Signal Mixing Aggregation for Message Passing Graph Neural Networks

• Provable Tempered Overfitting of Minimal Nets and Typical Nets Authors: Itamar Harel, William Hoza, Gal Vardi, Itay Evron, Nati Srebro, Daniel Soudry

NeurIPS Poster Provable Tempered Overfitting of Minimal Nets and Typical Nets

• The Implicit Bias of Gradient Descent on Separable Multiclass Data Authors: Hrithik Ravi, Clay Scott, Daniel Soudry, Yutong Wang

NeurIPS Poster The Implicit Bias of Gradient Descent on Separable Multiclass Data

• Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes Authors: Dan Qiao, Kaiqi Zhang, Esha Singh, Daniel Soudry, Yu-Xiang Wang

NeurIPS Poster Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes

• Exponential Quantum Communication Advantage in Distributed Inference and Learning Authors: Dar Gilboa, Hagay Michaeli, Daniel Soudry, Jarrod McClean

NeurIPS Poster Exponential Quantum Communication Advantage in Distributed Inference and Learning

• Unsupervised Discovery of Formulas for Mathematical Constants Authors: Michael Shalyt, Uri Seligmann, Itay Beit Halachmi, Ofir David, Rotem Elimelech, Ido Kaminer

NeurIPS Poster Unsupervised Discovery of Formulas for Mathematical Constants

• Incentivizing Quality Text Generation via Statistical Contracts Authors: Eden Saig, Ohad Einav, Inbal Talgam-Cohen

NeurIPS Poster Incentivizing Quality Text Generation via Statistical Contracts

• MAC Advice for Facility Location Mechanism Design Authors: Zohar Barak, Anupam Gupta, Inbal Talgam-Cohen

NeurIPS Poster MAC Advice for facility location mechanism design

• Contracting with a Learning Agent Authors: Guru Guruganesh, Yoav Kolumbus, Jon Schneider, Inbal Talgam-Cohen, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Joshua Wang, S. Weinberg

NeurIPS Poster Contracting with a Learning Agent

• Enhancing Consistency-Based Image Generation via Adversarially-Trained Classification and Energy-Based Discrimination Authors: Shelly Golan, Roy Ganz, Michael Elad

NeurIPS Poster Enhancing Consistency-Based Image Generation via Adversarialy-Trained Classification and Energy-Based Discrimination

• Wormhole Loss for Partial Shape Matching Authors: Amit Bracha, Thomas Dagès, Ron Kimmel

NeurIPS Poster Wormhole Loss for Partial Shape Matching

• Equivariant Machine Learning on Graphs with Nonlinear Spectral Filters Authors: Ya-Wei Eileen Lin, Ronen Talmon, Ron Levie

NeurIPS Poster Equivariant Machine Learning on Graphs with Nonlinear Spectral Filters

• Universal Rates for Active Learning Authors: Steve Hanneke, Amin Karbasi, Shay Moran, Grigoris Velegkas

NeurIPS Poster Universal Rates for Active Learning

• Learning-Augmented Algorithms with Explicit Predictors Authors: Marek Elias, Haim Kaplan, Yishay Mansour, Shay Moran

NeurIPS Poster Learning-Augmented Algorithms with Explicit Predictors

• Credit Attribution and Stable Compression Authors: Roi Livni, Shay Moran, Kobbi Nissim, Chirag Pabbaraju

NeurIPS Poster Credit Attribution and Stable Compression

• Improved Sample Complexity for Multiclass PAC Learning Authors: Steve Hanneke, Shay Moran, Qian Zhang

NeurIPS Poster Improved Sample Complexity for Multiclass PAC Learning

• Bandit-Feedback Online Multiclass Classification: Variants and Tradeoffs Authors: Yuval Filmus, Steve Hanneke, Idan Mehalel, Shay Moran

NeurIPS Poster Bandit-Feedback Online Multiclass Classification: Variants and Tradeoffs

• Fast Rates for Bandit PAC Multiclass Classification Authors: Liad Erez, Alon Peled-Cohen, Tomer Koren, Yishay Mansour, Shay Moran

NeurIPS Poster Fast Rates for Bandit PAC Multiclass Classification

• RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation Authors: Jeongyeol Kwon, Shie Mannor, Constantine Caramanis, Yonathan Efroni

NeurIPS Poster RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation

• Perceptual Fairness in Image Restoration Authors: Guy Ohayon, Michael Elad, Tomer Michaeli

NeurIPS Poster Perceptual Fairness in Image Restoration

• Hierarchical Uncertainty Exploration via Feedforward Posterior Trees Authors: Elias Nehme, Rotem Mulayoff, Tomer Michaeli

NeurIPS Poster Hierarchical Uncertainty Exploration via Feedforward Posterior Trees

• Classification Diffusion Models: Revitalizing Density Ratio Estimation Authors: Shahar Yadin, Noam Elata, Tomer Michaeli

NeurIPS Poster Classification Diffusion Models: Revitalizing Density Ratio Estimation

• Robust Conformal Prediction Using Privileged Information Authors: Shai Feldman, Yaniv Romano

NeurIPS Poster Robust Conformal Prediction Using Privileged Information

• Protected Test-Time Adaptation via Online Entropy Matching: A Betting Approach Authors: Yarin Bar, Shalev Shaer, Yaniv Romano

NeurIPS Poster Protected Test-Time Adaptation via Online Entropy Matching: A Betting Approach

• Learning on Large Graphs Using Intersecting Communities Authors: Ben Finkelshtein, Ismail Ceylan, Michael Bronstein, Ron Levie

NeurIPS Poster Learning on Large Graphs using Intersecting Communities

 

Tech.AI is thrilled to announce the acceptance of our researchers' groundbreaking papers at the prestigious International Conference on Machine Learning (ICML) 2024! Our dedicated researchers have been pushing the boundaries of AI research and innovation, and we couldn't be prouder of their achievements. We invite you to explore the cutting-edge work our researchers will be presenting at this esteemed conference.

     

• DNCs Require More Planning Steps

Yara Shamshoum · Nitzan Hodos · Yuval Sieradzki · Assaf Schuster

 

• A Bayesian Approach to Online Planning

Nir Greshler · David Ben Eli · Carmel Rabinovitz · Gabi Guetta · Liran Gispan · Guy Zohar · Aviv Tamar

 

• Test-Time Regret Minimization in Meta Reinforcement Learning

Mirco Mutti · Aviv Tamar

 

• How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers

Gon Buzaglo · Itamar Harel · Mor Shpigel Nacson · Alon Brutzkus · Nati Srebro · Daniel Soudry

 

• A Study of First-Order Methods with a Deterministic Relative-Error Gradient Oracle

Nadav Hallak · Kfir Levy

 

• Private and Federated Stochastic Convex Optimization: Efficient Strategies for Centralized Systems

Roie Reshef · Kfir Levy

 

• Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst Kernel

Uri Gadot · Kaixin Wang · Navdeep Kumar · Kfir Levy · Shie Mannor

 

• Dynamic Byzantine-Robust Learning: Adapting to Switching Byzantine Workers

Ron Dorfman · Naseem Yehya · Kfir Levy

 

• Efficient Value Iteration for s-rectangular Robust Markov Decision Processes

Navdeep Kumar · Kaixin Wang · Kfir Levy · Shie Mannor

 

• Fault Tolerant ML: Efficient Meta-Aggregation and Synchronous Training

Tehila Dahan · Kfir Levy

 

• The Perception-Robustness Tradeoff in Deterministic Image Restoration

Guy Ohayon · Tomer Michaeli · Michael Elad

 

• Early Time Classification with Accumulated Accuracy Gap Control

Liran Ringel · Regev Cohen · Daniel Freedman · Michael Elad · Yaniv Romano

 

• Rationality Report Cards: Assessing the Economic Rationality of Large Language Models

Narun Raman · Taylor Lundy · Samuel Joseph Amouyal · Yoav Levine · Kevin Leyton-Brown · Moshe Tennenholtz  

• Equivariant Deep Weight Space Alignment

Aviv Navon · Aviv Shamsian · Ethan Fetaya · Gal Chechik · Nadav Dym · Haggai Maron

 

• Equivariant Frames and the Impossibility of Continuous Canonicalization

Nadav Dym · Hannah Lawrence · Jonathan Siegel

 

• Position Paper: Future Directions in the Theory of Graph Machine Learning

Christopher Morris · Nadav Dym · Haggai Maron · Ismail Ceylan · Fabrizio Frasca · Ron Levie · Derek Lim · Michael Bronstein · Martin Grohe · Stefanie Jegelka

 

• Weisfeiler Leman for Euclidean Equivariant Machine Learning

Snir Hordan · Tal Amir · Nadav Dym

 

• Classification Under Strategic Self-Selection

Guy Horowitz · Yonatan Sommer · Moran Koren · Nir Rosenfeld

 

• One-Shot Strategic Classification Under Unknown Costs

Elan Rosenfeld · Nir Rosenfeld

 

• Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization

Yihan Du · Anna Winnicki · Gal Dalal · Shie Mannor · R Srikant  

• Sobolev Space Regularised Pre Density Models

Mark Kozdoba · Binyamin Perets · Shie Mannor  

• Improving Token-Based World Models with Parallel Observation Prediction

Lior Cohen · Kaixin Wang · Bingyi Kang · Shie Mannor

 

• Prospective Side Information for Latent MDPs

Jeongyeol Kwon · Yonathan Efroni · Shie Mannor · Constantine Caramanis  

• Learning the Target Network in Function Space

Kavosh Asadi · Yao Liu · Shoham Sabach · Ming Yin · Rasool Fakoor  

• MADA: Meta-Adaptive Optimizers through hyper-gradient Descent

Kaan Ozkara · Can Karakus · Parameswaran Raman · Mingyi Hong · Shoham Sabach · Branislav Kveton · Volkan Cevher

 

• Zero-Shot Unsupervised and Text-Based Audio Editing Using DDPM Inversion

Hila Manor · Tomer Michaeli

 

• Slicedit: Zero-Shot Video Editing With Text-to-Image Diffusion Models Using Spatio-Temporal Slices

Nathaniel Cohen · Vladimir Kulikov · Matan Kleiner · Inbar Huberman-Spiegelglas · Tomer Michaeli

 

• Subgraphormer: Unifying Subgraph GNNs and Graph Transformers via Graph Products

Guy Bar Shalom · Beatrice Bevilacqua · Haggai Maron

 

• On the Expressive Power of Spectral Invariant Graph Neural Networks

Bohang Zhang · Lingxiao Zhao · Haggai Maron

 

• Improved Generalization of Weight Space Networks via Augmentations

Aviv Shamsian · Aviv Navon · David Zhang · Yan Zhang · Ethan Fetaya · Gal Chechik · Haggai Maron

 

Prof. Ido Roll: Associate Professor and Senior Vice Provost for the Advancement of Learning and Teaching, Faculty of Education in Science and Technology and Faculty of Data and Decision Sciences Tuesday, June 18, 2024, 17:30-18:30, Faculty of Data and Decision Sciences, Bloomfield Building, 5th Floor, Room 526. Artificial intelligence tools have the potential to revolutionize higher education or become just another item on a long list of tools that couldn't break tradition. I will briefly present some specific developments in the field of artificial intelligence in higher education, followed by a discussion on the topic, both generally and at the Technion in particular. The only rules: no overgeneralizations (robots will kill/serve us all) and no excessive anecdotes (my niece wrote a Eurovision song in Swahili/Yiddish with ChatGPT). The meeting will be held in Hebrew Please register for the meeting here: הרשמה למפגשי בינה מלאכותית בחינוך, הטכניון (google.com)

בינה מלאכותית והחינוך הגבוה - לאן אנו צועדים?

פרופ' עדו רול: פרופסור חבר וסגן המשנה הבכיר לנשיא לקידום הלמידה וההוראה, הפקולטה לחינוך למדע וטכנולוגיה והפקולטה למדעי הנתונים וההחלטות

יום שלישי, 18.6.24, 17:30-18:30, הפקולטה למדעי הנתונים וההחלטות, בניין בלומפילד, קומה 5, חדר 526.

לכלי בינה מלאכותית פוטנציאל לעשות מהפיכה של ממש בחינוך הגבוה, או להיות עוד הזדמנות ברשימה ארוכה של כלים שלא יכלו למסורת. אציג בקצרה מספר התפתחויות ספציפיות לתחום של בינה מלאכותית בחינוך הגבוה ואז נערוך דיון בנושא באופן כללי ובטכניון בפרט. הכללים היחידים: בלי הכללות יתר (הרובוטים יהרגו/ישרתו את כולנו) ובלי יותר מדי אנקדוטות (אחיינית שלי כתבה שיר לאירוויזיון בסוואהילית/יידיש בעזרת צ׳אט).

On Monday, 27.5.2024, the Tech.AI Biomed conference, will be held in the Technion Visitors Center. Registration now open!  

A team at the Technion – Israel Institute of Technology's Faculty of Biomedical Engineering have developed a powerful artificial intelligence (AI) tool to help treat cancer.
more details

Advanced technology identifies pairs of drugs that can fight disease together, in microscopic doses. Prescribing a combination of two or more medications is already an established practice – known as combination therapy — that can prove highly effective.
more details

“People put more of themselves on social media than they realise,” says Prof. Avi (Avigdor) Gal Gal from the Faculty of Data and Decision Sciences, Technion. Ahead of World Suicide Prevention Day, students of the faculty banded together in a 3-day hackathon, looking for ways to recognize suicidal ideation and offer assistance.
more details

more details

Israel Innovation Authority to Invest NIS 36 million in Cutting-Edge Human Capital Programs for Quantum, AI, Cleantech, Foodtech, and Bio-Convergence Industries.
more details

Israel's Nevia Bio secures $3 M to build machine learning enabled health platform for women
more details