| 2026 | ACL | Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models. | Guy Kaplan, Michael Toker, Yuval Reif, Yonatan Belinkov, Roy Schwartz |
| 2026 | ACL | Vocab Diet: Reshaping the Vocabulary of LLMs via Vector Arithmetic. | Yuval Reif, Guy Kaplan, Roy Schwartz |
| 2026 | EACL | How Quantization Shapes Bias in Large Language Models. | Federico Marcuzzi, Xuefei Ning, Roy Schwartz, Iryna Gurevych |
| 2026 | ICALP | Tight Algorithm and Hardness for Submodular Linear Ordering. | Evan Abboud, Roy Schwartz |
| 2026 | STOC | A Poisson Process for Submodular Maximization. | Amit Ganz Rozenman, Ariel Kulik, Roy Schwartz, Mohit Singh |
| 2025 | EMNLP | Context Length Alone Hurts LLM Performance Despite Perfect Retrieval. | Yufeng Du, Minyang Tian, Srikanth Ronanki, Subendhu Rongali, Sravan Babu Bodapati, Aram Galstyan, Azton Wells, Roy Schwartz, Eliu A. Huerta, Hao Peng |
| 2025 | EMNLP | On Pruning State-Space LLMs. | Tamer Ghattas, Michael Hassid, Roy Schwartz |
| 2025 | ICLR | From Tokens to Words: On the Inner Lexicon of LLMs. | Guy Kaplan, Matanel Oren, Yuval Reif, Roy Schwartz |
| 2025 | IPCO | Separating Coverage and Submodular: Maximization Subject to a Cardinality Constraint. | Yuval Filmus, Roy Schwartz, Alexander V. Smal |
| 2024 | EMNLP | Transformers are Multi-State RNNs. | Matanel Oren, Michael Hassid, Yarden Nir, Yossi Adi, Roy Schwartz |
| 2024 | FOCS | On Approximating Cutwidth and Pathwidth. | Nikhil Bansal, Dor Katzelnick, Roy Schwartz |
| 2024 | NAACL | Beyond Performance: Quantifying and Mitigating Label Bias in LLMs. | Yuval Reif, Roy Schwartz |
| 2023 | AAAI | VASR: Visual Analogies of Situation Recognition. | Yonatan Bitton, Ron Yosef, Eliyahu Strugo, Dafna Shahaf, Roy Schwartz, Gabriel Stanovsky |
| 2023 | ACL | Fighting Bias With Bias: Promoting Model Robustness by Amplifying Dataset Biases. | Yuval Reif, Roy Schwartz |
| 2023 | ACL | Finding the SWEET Spot: Analysis and Improvement of Adaptive Inference in Low Resource Settings. | Daniel Rotem, Michael Hassid, Jonathan Mamou, Roy Schwartz |
| 2023 | ACL | Curating Datasets for Better Performance with Example Training Dynamics. | Aviad Sar-Shalom, Roy Schwartz |
| 2023 | ESA | A Tight Competitive Ratio for Online Submodular Welfare Maximization. | Amit Ganz, Pranav Nuti, Roy Schwartz |
| 2023 | ESA | An Improved Approximation Algorithm for the Max-3-Section Problem. | Dor Katzelnick, Aditya Pillai, Roy Schwartz, Mohit Singh |
| 2023 | ICCV | Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images. | Nitzan Bitton Guetta, Yonatan Bitton, Jack Hessel, Ludwig Schmidt, Yuval Elovici, Gabriel Stanovsky, Roy Schwartz |
| 2022 | ACL | Data Contamination: From Memorization to Exploitation. | Inbal Magar, Roy Schwartz |
| 2022 | ACL | ABC: Attention with Bounded-memory Control. | Hao Peng, Jungo Kasai, Nikolaos Pappas, Dani Yogatama, Zhaofeng Wu, Lingpeng Kong, Roy Schwartz, Noah A. Smith |
| 2022 | EMNLP | How Much Does Attention Actually Attend? Questioning the Importance of Attention in Pretrained Transformers. | Michael Hassid, Hao Peng, Daniel Rotem, Jungo Kasai, Ivan Montero, Noah A. Smith, Roy Schwartz |
| 2022 | NAACL | On the Limitations of Dataset Balancing: The Lost Battle Against Spurious Correlations. | Roy Schwartz, Gabriel Stanovsky |
| 2021 | EMNLP | Data Efficient Masked Language Modeling for Vision and Language. | Yonatan Bitton, Michael Elhadad, Gabriel Stanovsky, Roy Schwartz |
| 2021 | EMNLP | Expected Validation Performance and Estimation of a Random Variable's Maximum. | Jesse Dodge, Suchin Gururangan, Dallas Card, Roy Schwartz, Noah A. Smith |
| 2021 | EMNLP | Effects of Parameter Norm Growth During Transformer Training: Inductive Bias from Gradient Descent. | William Merrill, Vivek Ramanujan, Yoav Goldberg, Roy Schwartz, Noah A. Smith |
| 2021 | ICALP | Fault Tolerant Max-Cut. | Keren Censor-Hillel, Noa Marelly, Roy Schwartz, Tigran Tonoyan |
| 2021 | ICLR | Random Feature Attention. | Hao Peng, Nikolaos Pappas, Dani Yogatama, Roy Schwartz, Noah A. Smith, Lingpeng Kong |
| 2021 | NAACL | Automatic Generation of Contrast Sets from Scene Graphs: Probing the Compositional Consistency of GQA. | Yonatan Bitton, Gabriel Stanovsky, Roy Schwartz, Michael Elhadad |
| 2021 | NAACL | Extracting a Knowledge Base of Mechanisms from COVID-19 Papers. | Tom Hope, Aida Amini, David Wadden, Madeleine van Zuylen, Sravanthi Parasa, Eric Horvitz, Daniel S. Weld, Roy Schwartz, Hannaneh Hajishirzi |
| 2021 | STOC | The metric relaxation for | Roy Schwartz, Nitzan Tur |
| 2020 | ACL | A Formal Hierarchy of RNN Architectures. | William Merrill, Gail Weiss, Yoav Goldberg, Roy Schwartz, Noah A. Smith, Eran Yahav |
| 2020 | ACL | A Mixture of h - 1 Heads is Better than h Heads. | Hao Peng, Roy Schwartz, Dianqi Li, Noah A. Smith |
| 2020 | ACL | The Right Tool for the Job: Matching Model and Instance Complexities. | Roy Schwartz, Gabriel Stanovsky, Swabha Swayamdipta, Jesse Dodge, Noah A. Smith |
| 2020 | EMNLP | Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics. | Swabha Swayamdipta, Roy Schwartz, Nicholas Lourie, Yizhong Wang, Hannaneh Hajishirzi, Noah A. Smith, Yejin Choi |
| 2020 | SODA | Sticky Brownian Rounding and its Applications to Constraint Satisfaction Problems. | Sepehr Abbasi Zadeh, Nikhil Bansal, Guru Guruganesh, Aleksandar Nikolov, Roy Schwartz, Mohit Singh |
| 2019 | EMNLP | Show Your Work: Improved Reporting of Experimental Results. | Jesse Dodge, Suchin Gururangan, Dallas Card, Roy Schwartz, Noah A. Smith |
| 2019 | EMNLP | RNN Architecture Learning with Sparse Regularization. | Jesse Dodge, Roy Schwartz, Hao Peng, Noah A. Smith |
| 2019 | EMNLP | PaLM: A Hybrid Parser and Language Model. | Hao Peng, Roy Schwartz, Noah A. Smith |
| 2019 | EMNLP | Knowledge Enhanced Contextual Word Representations. | Matthew E. Peters, Mark Neumann, Robert L. Logan IV, Roy Schwartz, Vidur Joshi, Sameer Singh, Noah A. Smith |
| 2019 | ESA | Graph Balancing with Orientation Costs. | Roy Schwartz, Ran Yeheskel |
| 2019 | ICALP | A Tight Approximation for Submodular Maximization with Mixed Packing and Covering Constraints. | Eyal Mizrachi, Roy Schwartz, Joachim Spoerhase, Sumedha Uniyal |
| 2019 | NAACL | Inoculation by Fine-Tuning: A Method for Analyzing Challenge Datasets. | Nelson F. Liu, Roy Schwartz, Noah A. Smith |
| 2018 | ACL | Bridging CNNs, RNNs, and Weighted Finite-State Machines. | Roy Schwartz, Sam Thomson, Noah A. Smith |
| 2018 | EMNLP | Rational Recurrences. | Hao Peng, Roy Schwartz, Sam Thomson, Noah A. Smith |
| 2018 | EMNLP | SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference. | Rowan Zellers, Yonatan Bisk, Roy Schwartz, Yejin Choi |
| 2018 | NAACL | Annotation Artifacts in Natural Language Inference Data. | Suchin Gururangan, Swabha Swayamdipta, Omer Levy, Roy Schwartz, Samuel R. Bowman, Noah A. Smith |
| 2018 | NAACL | A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications. | Dongyeop Kang, Waleed Ammar, Bhavana Dalvi, Madeleine van Zuylen, Sebastian Kohlmeier, Eduard H. Hovy, Roy Schwartz |
| 2018 | SPAA | Trees for Vertex Cuts, Hypergraph Cuts and Minimum Hypergraph Bisection. | Harald Rcke, Roy Schwartz, Richard Stotz |
| 2017 | CoNLL | The Effect of Different Writing Tasks on Linguistic Style: A Case Study of the ROC Story Cloze Task. | Roy Schwartz, Maarten Sap, Ioannis Konstas, Leila Zilles, Yejin Choi, Noah A. Smith |
| 2017 | CoNLL | Automatic Selection of Context Configurations for Improved Class-Specific Word Representations. | Ivan Vulic, Roy Schwartz, Ari Rappoport, Roi Reichart, Anna Korhonen |
| 2017 | EACL | Story Cloze Task: UW NLP System. | Roy Schwartz, Maarten Sap, Ioannis Konstas, Leila Zilles, Yejin Choi, Noah A. Smith |
| 2017 | ICALP | Correlated Rounding of Multiple Uniform Matroids and Multi-Label Classification. | Shahar Chen, Dotan Di Castro, Zohar S. Karnin, Liane Lewin-Eytan, Joseph (Seffi) Naor, Roy Schwartz |
| 2017 | IPCO | Local Guarantees in Graph Cuts and Clustering. | Moses Charikar, Neha Gupta, Roy Schwartz |
| 2017 | SODA | Simplex Transformations and the Multiway Cut Problem. | Niv Buchbinder, Roy Schwartz, Baruch Weizman |
| 2016 | NAACL | Symmetric Patterns and Coordinations: Fast and Enhanced Representations of Verbs and Adjectives. | Roy Schwartz, Roi Reichart, Ari Rappoport |
| 2015 | ACL | How Well Do Distributional Models Capture Different Types of Semantic Knowledge? | Dana Rubinstein, Effi Levi, Roy Schwartz, Ari Rappoport |
| 2015 | CoNLL | Symmetric Pattern Based Word Embeddings for Improved Word Similarity Prediction. | Roy Schwartz, Roi Reichart, Ari Rappoport |
| 2015 | SODA | Comparing Apples and Oranges: Query Tradeoff in Submodular Maximization. | Niv Buchbinder, Moran Feldman, Roy Schwartz |
| 2015 | SODA | Online Submodular Maximization with Preemption. | Niv Buchbinder, Moran Feldman, Roy Schwartz |
| 2014 | COLING | Minimally Supervised Classification to Semantic Categories using Automatically Acquired Symmetric Patterns. | Roy Schwartz, Roi Reichart, Ari Rappoport |
| 2014 | SODA | Submodular Maximization with Cardinality Constraints. | Niv Buchbinder, Moran Feldman, Joseph Naor, Roy Schwartz |
| 2014 | SODA | Non-Uniform Graph Partitioning. | Robert Krauthgamer, Joseph Naor, Roy Schwartz, Kunal Talwar |
| 2014 | SIGCOMM | Calendaring for wide area networks. | Srikanth Kandula, Ishai Menache, Roy Schwartz, Spandana Raj Babbula |
| 2013 | EMNLP | Authorship Attribution of Micro-Messages. | Roy Schwartz, Oren Tsur, Ari Rappoport, Moshe Koppel |
| 2013 | IPCO | All-or-Nothing Generalized Assignment with Application to Scheduling Advertising Campaigns. | Ron Adany, Moran Feldman, Elad Haramaty, Rohit Khandekar, Baruch Schieber, Roy Schwartz, Hadas Shachnai, Tami Tamir |
| 2013 | STOC | Simplex partitioning via exponential clocks and the multiway cut problem. | Niv Buchbinder, Joseph Naor, Roy Schwartz |
| 2013 | WSDM | Rank quantization. | Ravi Kumar, Ronny Lempel, Roy Schwartz, Sergei Vassilvitskii |
| 2012 | COLING | Learnability-Based Syntactic Annotation Design. | Roy Schwartz, Omri Abend, Ari Rappoport |
| 2012 | COLT | Unsupervised SVMs: On the Complexity of the Furthest Hyperplane Problem. | Zohar Shay Karnin, Edo Liberty, Shachar Lovett, Roy Schwartz, Omri Weinstein |
| 2012 | FOCS | A Tight Linear Time (1/2)-Approximation for Unconstrained Submodular Maximization. | Niv Buchbinder, Moran Feldman, Joseph Naor, Roy Schwartz |
| 2011 | ACL | Neutralizing Linguistically Problematic Annotations in Unsupervised Dependency Parsing Evaluation. | Roy Schwartz, Omri Abend, Roi Reichart, Ari Rappoport |
| 2011 | ESA | Improved Approximations for k-Exchange Systems - (Extended Abstract). | Moran Feldman, Joseph Naor, Roy Schwartz, Justin Ward |
| 2011 | FOCS | Min-max Graph Partitioning and Small Set Expansion. | Nikhil Bansal, Uriel Feige, Robert Krauthgamer, Konstantin Makarychev, Viswanath Nagarajan, Joseph Naor, Roy Schwartz |
| 2011 | FOCS | A Unified Continuous Greedy Algorithm for Submodular Maximization. | Moran Feldman, Joseph Naor, Roy Schwartz |
| 2011 | ICALP | Nonmonotone Submodular Maximization via a Structural Continuous Greedy Algorithm - (Extended Abstract). | Moran Feldman, Joseph Naor, Roy Schwartz |
| 2009 | SODA | Partitioning graphs into balanced components. | Robert Krauthgamer, Joseph Naor, Roy Schwartz |
| 2008 | STOC | Sdp gaps and ugc hardness for multiway cut, 0-extension, and metric labeling. | Rajsekar Manokaran, Joseph Naor, Prasad Raghavendra, Roy Schwartz |
| 2005 | STOC | Balanced metric labeling. | Joseph Naor, Roy Schwartz |
| 2004 | SODA | The directed circular arrangement problem. | Joseph Naor, Roy Schwartz |