Publications

Philipp Emanuel Weidmann, Allen Roush, Judah Goldfeder, Sanjay Basu, Ravid Shwartz Ziv (2026). Don't Repeat Yourself: Stopping Verbatim Loops at Sampling Time. arXiv, 2026.

PDF Cite arXiv

Philipp Emanuel Weidmann, Allen Roush, Judah Goldfeder, Sanjay Basu, Ravid Shwartz Ziv (2026). XTC: Head-Aware Sampling by Excluding Top Choices. arXiv, 2026.

PDF Cite arXiv

Ruichen Xu, Jingxiang Qu, Wenhan Gao, Jiaxing Zhang, Linsey Pang, Ravid Shwartz Ziv, Yann LeCun, Yuefan Deng (2026). HP-JEPA: Hierarchical Partitioning for Multi-Resolution Graph Joint-Embedding Predictive Learning. arXiv, 2026.

PDF Cite arXiv

Georgios Ioannides, Adrian Kieback, Judah Goldfeder, Linsey Pang, Aman Chadha, Aaron Elkins, Yann LeCun, Ravid Shwartz Ziv (2026). S-JEPA: Soft Clustering Anchors for Self-Supervised Speech Representation Learning. arXiv, 2026.

PDF Cite Code arXiv

Daniel Ben-Levi, Judah Goldfeder, Weiliang Zhao, Raz Lapid, Amit LeVi, Allen G. Roush, Ravid Shwartz Ziv, Hod Lipson (2026). Mirage Probes: How Vision Models Fake Visual Understanding. ICML 2026 EMM-QA Workshop (Spotlight).

PDF Cite arXiv Publication

Nadav Timor, Ravid Shwartz Ziv, Micah Goldblum, Yann LeCun, David Harel (2026). On Training in Imagination. arXiv, 2026.

PDF Cite arXiv

Eitan Shaar, Ariel Shaulov, Yalcin Tur, Gal Chechik, Ravid Shwartz Ziv (2026). Latent Transfer Attack: Adversarial Examples via Generative Latent Spaces. arXiv, 2026.

PDF Cite arXiv

Judah Goldfeder, Philippe Wyder, Yann LeCun, Ravid Shwartz Ziv (2026). AI Must Embrace Specialization via Superhuman Adaptable Intelligence. arXiv, 2026.

PDF Cite arXiv

Sunny Sanyal, Ravid Shwartz Ziv, Alexandros G. Dimakis, Sujay Sanghavi (2026). When Attention Collapses: How Degenerate Layers in LLMs Enable Smaller, Stronger Models. TMLR 2026.

PDF Cite Code Journal version

Pierre-Louis Favreau, Jean-Pierre Lo, Clement Guiguet, Charles Simon-Meunier, Nicolas Dehandschoewercker, Allen G. Roush, Judah Goldfeder, Ravid Shwartz Ziv (2026). Do Multi-Agents Dream of Electric Screens? Achieving Perfect Accuracy on AndroidWorld Through Task Decomposition. Preprint.

PDF Cite Code arXiv

Elias Hossain, Shubhashis Roy Dipta, Subash Neupane, Rajib Rana, Ravid Shwartz Ziv, Ivan Garibay, Niloofar Yousefi (2026). UAT-LITE: Inference-Time Uncertainty-Aware Attention for Pretrained Transformers. arXiv, 2026.

PDF Cite arXiv

Arian Khorasani, Nathaniel Chen, Yug D Oswal, Akshat Santhana Gopalan, Egemen Kolemen, Ravid Shwartz Ziv (2026). Beyond the Loss Curve: Scaling Laws, Active Learning, and the Limits of Learning from Exact Posteriors. arXiv, 2026.

PDF Cite arXiv

Georgios Ioannides, Adrian Kieback, Judah Goldfeder, Linsey Pang, Aman Chadha, Aaron Elkins, Yann LeCun, Ravid Shwartz Ziv (2026). Soft Clustering Anchors for Self-Supervised Speech Representation Learning in Joint Embedding Prediction Architectures. arXiv, 2026.

PDF Cite Code arXiv

Aparna Elangovan, Lei Xu, Mahsa Elyasi, Ismail Akdulum, Mehmet Aksakal, Enes Gurun, Brian Hur, Saab Mansour, Ravid Shwartz Ziv, Karin Verspoor, Dan Roth (2026). The Illusion of AI Expertise Under Uncertainty: Navigating Elusive Ground Truth via a Probabilistic Paradigm. arXiv, 2026.

PDF Cite arXiv

Georgios Ioannides, Christos Constantinou, Aman Chadha, Aaron Elkins, Linsey Pang, Ravid Shwartz Ziv, Yann LeCun (2025). JEPA as a Neural Tokenizer: Learning Robust Speech Representations with Density Adaptive Attention. NeurIPS 2025, UniReps Workshop.

PDF Cite arXiv

Allen Roush, Devin Gonier, John Hines, Judah Goldfeder, Philippe Martin Wyder, Sanjay Basu, Ravid Shwartz Ziv (2025). A superpersuasive autonomous policy debating system. AAAI 2026 CLIP Workshop.

PDF Cite Code arXiv

Amit LeVi, Raz Lapid, Rom Himelstein, Chaim Baskin, Ravid Shwartz Ziv, Avi Mendelson (2025). You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations. ICML 2026 AdaptFM Workshop.

PDF Cite arXiv

Semyon Lomasov, Judah Goldfeder, Mehmet Hamza Erol, Matthew So, Yao Yan, Addison Howard, Nathan Kutz, Ravid Shwartz Ziv (2025). Exploring Human-AI Conceptual Alignment through the Prism of Chess. NeurIPS 2025 Creative AI Track.

PDF Cite Code arXiv Proceedings

Alexandra Yost, Shreyans Jain, Shivam Raval, Grant Corser, Allen Roush, Nina Xu, Jacqueline Hammack, Ravid Shwartz Ziv, Amirali Abdullah (2025). Measure what Matters: Psychometric Evaluation of AI with Situational Judgment Tests. Preprint.

PDF Cite Code arXiv

Samuel Paech, Allen Roush, Judah Goldfeder, Ravid Shwartz Ziv (2025). Antislop: A Comprehensive Framework for Identifying and Eliminating Repetitive Patterns in Language Models. ICLR 2026.

PDF Cite Code arXiv Publication

Enrique Queipo-de-Llano, Álvaro Arroyo, Federico Barbero, Xiaowen Dong, Michael Bronstein, Yann LeCun, Ravid Shwartz Ziv (2025). Attention Sinks and Compression Valleys in LLMs are Two Sides of the Same Coin. ICLR 2026.

PDF Cite arXiv Publication

Denis Janiak, Jakub Binkowski, Albert Sawczyn, Bogdan Gabrys, Ravid Shwartz Ziv, Tomasz Kajdanowicz (2025). The Illusion of Progress: Re-evaluating Hallucination Detection in LLMs. EMNLP 2025.

PDF Cite arXiv Publication

Oscar Skean, Md Rifat Arefin, Dan Zhao, Niket Nikul Patel, Jalal Naghiyev, Yann LeCun, Ravid Shwartz Ziv (2025). Layer by Layer: Uncovering Hidden Representations in Language Models. ICML 2025 (Oral).

PDF Cite Code arXiv Proceedings Oral presentation

Rizwan Qureshi, Ranjan Sapkota, Abbas Shah, Amgad Muneer, Anas Zafar, Ashmal Vayani, Maged Shoman, Abdelrahman B. M. Eldaly, Kai Zhang, Ferhat Sadak, Shaina Raza, Xinqi Fan, Ravid Shwartz Ziv, Hong Yan, Vinjia Jain, Aman Chadha, Manoj Karkee, Jia Wu, Seyedali Mirjalili (2025). Thinking Beyond Tokens: From Brain-Inspired Intelligence to Cognitive Foundations for Artificial General Intelligence and its Societal Impact. Preprint.

PDF Cite arXiv

Aadim Nepal, Safal Shrestha, Anubhav Shrestha, Minwu Kim, Jalal Naghiyev, Ravid Shwartz Ziv, Keith Ross (2025). Layer Importance for Mathematical Reasoning is Forged in Pre-Training and Invariant after Post-Training. NeurIPS 2025 MATH-AI Workshop.

PDF Cite arXiv Publication

Chen Shani, Liron Soffer, Dan Jurafsky, Yann LeCun, Ravid Shwartz Ziv (2025). From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning. ICLR 2026.

PDF Cite arXiv Publication

Tim G. J. Rudner, Xiang Pan, Yucen Lily Li, Ravid Shwartz Ziv, Andrew Gordon Wilson (2025). Fine-Tuning with Uncertainty-Aware Priors Makes Vision and Language Foundation Models More Reliable. AISTATS 2025.

PDF Cite Code Publication

Alex Reneau, Jerry Yao-Chieh Hu, Zhongfang Zhuang, Ting-Chun Liu, Xiang He, Judah Goldfeder, Nadav Timor, Allen G Roush, Ravid Shwartz Ziv (2025). NdLinear: Preserving Multi-Dimensional Structure for Parameter-Efficient Neural Networks. arXiv, 2025.

PDF Cite Code arXiv

Tal Zeevi, Ravid Shwartz Ziv, Yann LeCun, Lawrence H. Staib, John A. Onofrey (2024). Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation. CVPR 2025.

PDF Cite Code arXiv Publication

Md Rifat Arefin, Gopeshh Raaj Subbaraj, Nicolas Gontier, Yann LeCun, Irina Rish, Ravid Shwartz Ziv, Christopher Pal (2024). Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning. ICLR 2025.

PDF Cite arXiv Proceedings

Minh Nhat Nguyen, Andrew Baker, Clement Neo, Allen Roush, Andreas Kirsch, Ravid Shwartz Ziv (2024). Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs. ICLR 2025 (Oral).

PDF Cite Code arXiv Proceedings

Colin White, Samuel Dooley, Manley Roberts, Arka Pal, Ben Feuer, Siddhartha Jain, Ravid Shwartz Ziv, Neel Jain, Khalid Saifullah, Sreemanti Dey, Shubh-Agrawal, Sandeep Singh Sandha, Siddartha Naidu, Chinmay Hegde, Yann LeCun, Tom Goldstein, Willie Neiswanger, Micah Goldblum (2024). LiveBench: A Challenging, Contamination-Limited LLM Benchmark. ICLR 2025 (Spotlight).

PDF Cite Code arXiv

Roush Allen, Shabazz Yusuf, Balaji Arvind, Zhang Peter, Mezza Stefano, Zhang Markus, Basu Sanjay, Vishwanath Sriram, Fatemi Mehdi, Ravid Shwartz Ziv (2024). OpenDebateEvidence: A Massive-Scale Argument Mining and Summarization Dataset. In NeurIPS.

PDF Cite Dataset

Ravid Shwartz Ziv, Balestriero Randall, Kawaguchi Kenji, Rudner Tim GJ, LeCun Yann (2023). An Information Theory Perspective on Variance-Invariance-Covariance Regularization. In NeurIPS.

PDF Cite

Ravid Shwartz Ziv, Goldblum Micah, Li Yucen, Bruss C. Bayan, Wilson Andrew G. (2023). Back to Basics: Revisiting Standard Deep Learning Components for Class Imbalance. In NeurIPS.

PDF Cite DOI

Ravid Shwartz Ziv, Ravid, Shwartz-Ziv, Yann, LeCun (2023). To Compress or Not to Compress--Self-Supervised Learning and Information Theory: A Review. In Entropy.

PDF Cite DOI

Ravid Shwartz Ziv, Randall, Balestriero, Yann, LeCun (2022). What Do We Maximize in Self-Supervised Learning?. In ICML 2022: Pre-training: Perspectives, Pitfalls, and Paths Forward workshop.

PDF Cite

Ravid Shwartz Ziv, Micah, Goldblum, Hossein, Souri, Sanyam, Kapoor, Chen, Zhu, Yann, LeCun, Andrew, Wilson (2022). Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors. In NeurIPS 2022.

PDF Cite Code Video

Ravid Shwartz Ziv, Armon Amitai (2022). Tabular Data: Deep Learning is Not All You Need. In Information Fusion.

PDF Cite Video

Zoe Piran(?), Ravid Shwartz Ziv(?), Naftali Tishby (2020). The Dual Information Bottleneck.

PDF Cite Code

Ido Maor, Ravid Shwartz Ziv, Libi Feigin, Yishai Elyada, Haim Sompolinsky, Adi Mizrahi (2020). Neural Correlates of Learning Pure Tones or Natural Sounds in the Auditory Cortex. Frontiers in Neural Circuits.

PDF Cite

Ravid Shwartz Ziv, Alexander A Alemi (2020). Information in Infinite Ensembles of Infinitely-Wide Neural Networks. In The Symposium on Advances in Approximate Bayesian Inference.

PDF Cite Code

Ben-Ari Itamar(?), Ravid Shwartz Ziv(?) (2018). Attentioned Convolutional LSTM Inpaintingv Network for Anomaly Detection in Videos. NIPS 2018 Workshop on Systems for ML.

PDF Cite

Ravid Shwartz Ziv(?), Ben-Ari Itamar(?) (2017). Sequence Modeling Using a Memory Controller Extension for LSTM. NIPS 2017 Time Series Workshop.

PDF Cite

Ravid Shwartz Ziv, Tishby, Naftali (2017). Opening the Black Box of Deep Neural Networks via Information.

PDF Cite Code Article

Ravid Shwartz Ziv, Armon Amitai (2017). Tabular Data: Deep Learning is Not All You Need. In TICML 2021 Workshop AutoML.

PDF Cite

Faivishevsky Lev, Muppalla Ashwin, Ravid Shwartz Ziv, Laperdon Ronen, Melloul Benjamin, Hollander Tahi, Amitai Armon (0001). Automated Testing of Graphics Units by Deep-Learning Detection of Visual Anomalies. NIPS 2018 Machine Learning for Systems Workshop.

PDF Cite