| 2026 | ACL | Your LLM Agents are Temporally Blind: The Misalignment Between Tool Use Decisions and Human Time Perception. | Yize Cheng, Arshia Soltani Moakhar, Chenrui Fan, Parsa Hosseini, Kazem Faghih, Zahra Sodagar, Wenxiao Wang, Soheil Feizi |
| 2026 | ACL | Schoenfeld's Anatomy of Mathematical Reasoning by Language Models. | Ming Li, Chenrui Fan, Yize Cheng, Soheil Feizi, Tianyi Zhou |
| 2026 | EACL | Decomposition-Enhanced Training for Post-Hoc Attributions in Language Models. | Sriram Balasubramanian, Samyadeep Basu, Koustava Goswami, Ryan Anthony Rossi, Varun Manjunatha, Roshan Santhosh, Ruiyi Zhang, Soheil Feizi, Nedim Lipka |
| 2026 | EACL | Attacker's Noise Can Manipulate Your Audio-based LLM in the Real World. | Vinu Sankar Sadasivan, Soheil Feizi, Rajiv Mathews, Lun Wang |
| 2025 | ACL | RePanda: Pandas-powered Tabular Verification and Reasoning. | Atoosa Malemir Chegini, Keivan Rezaei, Hamid Eghbalzadeh, Soheil Feizi |
| 2025 | ACL | Almost AI, Almost Human: The Challenge of Detecting AI-Polished Writing. | Shoumik Saha, Soheil Feizi |
| 2025 | CVPR | Understanding the Effect of using Semantically Meaningful Tokens for Visual Representation Learning. | Neha Mukund Kalibhat, Priyatham Kattakinda, Sumit Nawathe, Arman Zarei, Nikita Seleznev, Samuel Sharpe, Senthil Kumar, Soheil Feizi |
| 2025 | EMNLP | A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models. | Sriram Balasubramanian, Samyadeep Basu, Soheil Feizi |
| 2025 | EMNLP | DyePack: Provably Flagging Test Set Contamination in LLMs Using Backdoors. | Yize Cheng, Wenxiao Wang, Mazda Moayeri, Soheil Feizi |
| 2025 | EMNLP | Tool Preferences in Agentic LLMs are Unreliable. | Kazem Faghih, Wenxiao Wang, Yize Cheng, Siddhant Bharti, Gaurang Sriramanan, Sriram Balasubramanian, Parsa Hosseini, Soheil Feizi |
| 2025 | ICLR | How Learnable Grids Recover Fine Detail in Low Dimensions: A Neural Tangent Kernel Analysis of Multigrid Parametric Encodings. | Samuel Audia, Soheil Feizi, Matthias Zwicker, Dinesh Manocha |
| 2025 | ICLR | Rethinking Artistic Copyright Infringements In the Era Of Text-to-Image Generative Models. | Mazda Moayeri, Sriram Balasubramanian, Samyadeep Basu, Priyatham Kattakinda, Atoosa Malemir Chegini, Robert Brauneis, Soheil Feizi |
| 2025 | ICLR | Unearthing Skill-level Insights for Understanding Trade-offs of Foundation Models. | Mazda Moayeri, Vidhisha Balachandran, Varun Chandrasekaran, Safoora Yousefi, Thomas Fel, Soheil Feizi, Besmira Nushi, Neel Joshi, Vibhav Vineet |
| 2025 | PERCOM | Mitigating Compositional Failures in Text-to-Image Models with Causal Text Embedding Refinement. | Arman Zarei, Keivan Rezaei, Samyadeep Basu, Mehrdad Saberi, Mazda Moayeri, Priyatham Kattakinda, Adrienne Raglin, Anjon Basak, Soheil Feizi |
| 2024 | AAAI | Strong Baselines for Parameter-Efficient Few-Shot Fine-Tuning. | Samyadeep Basu, Shell Xu Hu, Daniela Massiceti, Soheil Feizi |
| 2024 | AAAI | Measuring Self-Supervised Representation Quality for Downstream Classification Using Discriminative Features. | Neha Mukund Kalibhat, Kanika Narang, Hamed Firooz, Maziar Sanjabi, Soheil Feizi |
| 2024 | EMNLP | Distilling Knowledge from Text-to-Image Generative Models Improves Visio-Linguistic Reasoning in CLIP. | Samyadeep Basu, Shell Xu Hu, Maziar Sanjabi, Daniela Massiceti, Soheil Feizi |
| 2024 | EMNLP | IntCoOp: Interpretability-Aware Vision-Language Prompt Tuning. | Soumya Suvra Ghosal, Samyadeep Basu, Soheil Feizi, Dinesh Manocha |
| 2024 | ICLR | Localizing and Editing Knowledge In Text-to-Image Generative Models. | Samyadeep Basu, Nanxuan Zhao, Vlad I. Morariu, Soheil Feizi, Varun Manjunatha |
| 2024 | ICLR | PRIME: Prioritizing Interpretability in Failure Mode Extraction. | Keivan Rezaei, Mehrdad Saberi, Mazda Moayeri, Soheil Feizi |
| 2024 | ICLR | Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks. | Mehrdad Saberi, Vinu Sankar Sadasivan, Keivan Rezaei, Aounon Kumar, Atoosa Malemir Chegini, Wenxiao Wang, Soheil Feizi |
| 2024 | ICLR | DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness. | Shoumik Saha, Wenxiao Wang, Yigitcan Kaya, Soheil Feizi, Tudor Dumitras |
| 2024 | ICML | On Mechanistic Knowledge Localization in Text-to-Image Generative Models. | Samyadeep Basu, Keivan Rezaei, Priyatham Kattakinda, Vlad I. Morariu, Nanxuan Zhao, Ryan A. Rossi, Varun Manjunatha, Soheil Feizi |
| 2024 | ICML | Fast Adversarial Attacks on Language Models In One GPU Minute. | Vinu Sankar Sadasivan, Shoumik Saha, Gaurang Sriramanan, Priyatham Kattakinda, Atoosa Malemir Chegini, Soheil Feizi |
| 2024 | WACV | Data-Centric Debugging: mitigating model failures via targeted image retrieval. | Sahil Singla, Atoosa Malemir Chegini, Mazda Moayeri, Soheil Feizi |
| 2023 | AAAI | Goal-Conditioned Q-learning as Knowledge Distillation. | Alexander Levine, Soheil Feizi |
| 2023 | BMVC | Adapting Self-Supervised Representations to Multi-Domain Setups. | Neha Mukund Kalibhat, Samuel Sharpe, Jeremy Goodsitt, C. Bayan Bruss, Soheil Feizi |
| 2023 | CVPR | Text2Concept: Concept Activation Vectors Directly from Text. | Mazda Moayeri, Keivan Rezaei, Maziar Sanjabi, Soheil Feizi |
| 2023 | CVPR | CUDA: Convolution-Based Unlearnable Datasets. | Vinu Sankar Sadasivan, Mahdi Soltanolkotabi, Soheil Feizi |
| 2023 | ICCV | Towards Improved Input Masking for Convolutional Neural Networks. | Sriram Balasubramanian, Soheil Feizi |
| 2023 | ICLR | Hard-Meta-Dataset++: Towards Understanding Few-Shot Performance on Difficult Tasks. | Samyadeep Basu, Megan Stanley, John Bronskill, Soheil Feizi, Daniela Massiceti |
| 2023 | ICLR | Provable Robustness against Wasserstein Distribution Shifts via Input Randomization. | Aounon Kumar, Alexander Levine, Tom Goldstein, Soheil Feizi |
| 2023 | ICLR | Certifiably Robust Policy Learning against Adversarial Multi-Agent Communication. | Yanchao Sun, Ruijie Zheng, Parisa Hassanzadeh, Yongyuan Liang, Soheil Feizi, Sumitra Ganesh, Furong Huang |
| 2023 | ICML | Identifying Interpretable Subspaces in Image Representations. | Neha Mukund Kalibhat, Shweta Bhardwaj, C. Bayan Bruss, Hamed Firooz, Maziar Sanjabi, Soheil Feizi |
| 2023 | ICML | Text-To-Concept (and Back) via Cross-Model Alignment. | Mazda Moayeri, Keivan Rezaei, Maziar Sanjabi, Soheil Feizi |
| 2023 | ICML | Run-off Election: Improved Provable Defense against Data Poisoning Attacks. | Keivan Rezaei, Kiarash Banihashem, Atoosa Malemir Chegini, Soheil Feizi |
| 2022 | AISTATS | Provable Adversarial Robustness for Fractional Lp Threat Models. | Alexander Levine, Soheil Feizi |
| 2022 | CVPR | Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detection. | Jiang Liu, Alexander Levine, Chun Pong Lau, Rama Chellappa, Soheil Feizi |
| 2022 | CVPR | A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributes. | Mazda Moayeri, Phillip Pope, Yogesh Balaji, Soheil Feizi |
| 2022 | ICLR | Salient ImageNet: How to discover spurious features in Deep Learning? | Sahil Singla, Soheil Feizi |
| 2022 | ICLR | Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100. | Sahil Singla, Surbhi Singla, Soheil Feizi |
| 2022 | ICLR | Policy Smoothing for Provably Robust Reinforcement Learning. | Aounon Kumar, Alexander Levine, Soheil Feizi |
| 2022 | ICML | Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation. | Wenxiao Wang, Alexander Levine, Soheil Feizi |
| 2022 | ICML | FOCUS: Familiar Objects in Common and Uncommon Settings. | Priyatham Kattakinda, Soheil Feizi |
| 2021 | AAAI | Winning Lottery Tickets in Deep Generative Models. | Neha Mukund Kalibhat, Yogesh Balaji, Soheil Feizi |
| 2021 | AISTATS | GANs with Conditional Independence Graphs: On Subadditivity of Probability Divergences. | Mucong Ding, Constantinos Daskalakis, Soheil Feizi |
| 2021 | ICCV | Sample Efficient Detection and Classification of Adversarial Attacks via Self-Supervised Embeddings. | Mazda Moayeri, Soheil Feizi |
| 2021 | ICCV | Low Curvature Activations Reduce Overfitting in Adversarial Training. | Vasu Singla, Sahil Singla, Soheil Feizi, David Jacobs |
| 2021 | ICLR | Deep Partition Aggregation: Provable Defenses against General Poisoning Attacks. | Alexander Levine, Soheil Feizi |
| 2021 | ICLR | Fantastic Four: Differentiable and Efficient Bounds on Singular Values of Convolution Layers. | Sahil Singla, Soheil Feizi |
| 2021 | ICLR | Understanding Over-parameterization in Generative Adversarial Networks. | Yogesh Balaji, Mohammadmahdi Sajedi, Neha Mukund Kalibhat, Mucong Ding, Dominik Stger, Mahdi Soltanolkotabi, Soheil Feizi |
| 2021 | ICLR | Influence Functions in Deep Learning Are Fragile. | Samyadeep Basu, Phillip Pope, Soheil Feizi |
| 2021 | ICLR | Perceptual Adversarial Robustness: Defense Against Unseen Threat Models. | Cassidy Laidlaw, Sahil Singla, Soheil Feizi |
| 2021 | ICML | Improved, Deterministic Smoothing for L | Alexander Levine, Soheil Feizi |
| 2021 | ICML | Skew Orthogonal Convolutions. | Sahil Singla, Soheil Feizi |
| 2021 | UAI | Unsupervised anomaly detection with adversarial mirrored autoencoders. | Gowthami Somepalli, Yexin Wu, Yogesh Balaji, Bhanukiran Vinzamuri, Soheil Feizi |
| 2020 | AAAI | Adversarially Robust Distillation. | Micah Goldblum, Liam Fowl, Soheil Feizi, Tom Goldstein |
| 2020 | AAAI | Robustness Certificates for Sparse Adversarial Attacks by Randomized Ablation. | Alexander Levine, Soheil Feizi |
| 2020 | AAAI | Maximum Likelihood Embedding of Logistic Random Dot Product Graphs. | Luke J. O'Connor, Muriel Mdard, Soheil Feizi |
| 2020 | AISTATS | Wasserstein Smoothing: Certified Robustness against Wasserstein Adversarial Attacks. | Alexander Levine, Soheil Feizi |
| 2020 | AISTATS | Adversarial Robustness of Flow-Based Generative Models. | Phillip Pope, Yogesh Balaji, Soheil Feizi |
| 2020 | ECCV | Deep k-NN Defense Against Clean-Label Data Poisoning Attacks. | Neehar Peri, Neal Gupta, W. Ronny Huang, Liam Fowl, Chen Zhu, Soheil Feizi, Tom Goldstein, John P. Dickerson |
| 2020 | ICML | Second-Order Provable Defenses against Adversarial Attacks. | Sahil Singla, Soheil Feizi |
| 2020 | ICML | On Second-Order Group Influence Functions for Black-Box Predictions. | Samyadeep Basu, Xuchen You, Soheil Feizi |
| 2020 | ICML | Curse of Dimensionality on Randomized Smoothing for Certifiable Robustness. | Aounon Kumar, Alexander Levine, Tom Goldstein, Soheil Feizi |
| 2019 | ICCV | Normalized Wasserstein for Mixture Distributions With Applications in Adversarial Learning and Domain Adaptation. | Yogesh Balaji, Rama Chellappa, Soheil Feizi |
| 2019 | ICLR | Are adversarial examples inevitable? | Ali Shafahi, W. Ronny Huang, Christoph Studer, Soheil Feizi, Tom Goldstein |
| 2019 | ICML | Entropic GANs meet VAEs: A Statistical Approach to Compute Sample Likelihoods in GANs. | Yogesh Balaji, Hamed Hassani, Rama Chellappa, Soheil Feizi |
| 2019 | ICML | Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation. | Sahil Singla, Eric Wallace, Shi Feng, Soheil Feizi |
| 2012 | ACSSC | Empirical rate-distortion study of compressive sensing-based joint source-channel coding. | Muriel L. Rambeloarison, Soheil Feizi, Georgios Angelopoulos, Muriel Mdard |
| 2012 | ICASSP | Time-stampless adaptive nonuniform sampling for stochastic signals. | Soheil Feizi, Vivek K. Goyal, Muriel Mdard |
| 2010 | ISIT | Cases where finding the minimum entropy coloring of a characteristic graph is a polynomial time problem. | Soheil Feizi, Muriel Mdard |