Ehsan Abbasnejad

Certified but Fooled! Breaking Certified Defenses with Ghost Certificates AAAI 2026 Truth as a Trajectory: What Internal Representations Reveal About Large Language Model Reasoning ACL 2026 Bayesian Low-Rank Learning (Bella): A Practical Approach to Bayesian Neural Networks AAAI 2025 Do Deep Neural Network Solutions Form a Star Domain? ICLR 2025 Do We Always Need the Simplicity Bias? Looking for Optimal Inductive Biases in the Wild CVPR 2025 RandLoRA: Full rank parameter-efficient fine-tuning of large models ICLR 2025 Synergy and Diversity in CLIP: Enhancing Performance Through Adaptive Backbone Ensembling ICLR 2025 Towards Higher Effective Rank in Parameter-Efficient Fine-tuning using Khatri-Rao Product ICCV 2025 BLURD: Benchmarking and Learning using a Unified Rendering and Diffusion Model NeurIPS 2024 BRUSLEATTACK: A QUERY-EFFICIENT SCORE- BASED BLACK-BOX SPARSE ADVERSARIAL ATTACK ICLR 2024 Knowledge Composition using Task Vectors with Learned Anisotropic Scaling NeurIPS 2024 Neural Redshift: Random Networks are not Random Functions CVPR 2024 Selective Mixup Helps with Distribution Shifts, But Not (Only) because of Mixup ICML 2024 Semantic Role Labeling Guided Out-of-distribution Detection COLING 2024 Energy-based Self-Training and Normalization for Unsupervised Domain Adaptation ICCV 2023 Feature-Space Bayesian Adversarial Learning Improved Malware Detector Robustness AAAI 2023 ID and OOD Performance Are Sometimes Inversely Correlated on Real-world Datasets NeurIPS 2023 LAVA: Label-Efficient Visual Learning and Adaptation WACV 2023 ProtoCon: Pseudo-Label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-Supervised Learning CVPR 2023 RanPAC: Random Projections and Pre-trained Models for Continual Learning NeurIPS 2023 Active Learning by Feature Mixing CVPR 2022 Astock: A New Dataset and Automated Stock Trading based on Stock-specific News Analyzing Model EMNLP 2022 Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions With Superior OOD Generalization CVPR 2022 ForeSI: Success-Aware Visual Navigation Agent WACV 2022 Predicting Is Not Understanding: Recognizing and Addressing Underspecification in Machine Learning ECCV 2022 Progressive Class Semantic Matching for Semi-supervised Text Classification NAACL 2022 Truncated Matrix Power Iteration for Differentiable DAG Learning NeurIPS 2022 UOA at the FinNLP-2022 ERAI Task: Leveraging the Class Label Description for Financial Opinion Mining EMNLP 2022 All Labels Are Not Created Equal: Enhancing Semi-Supervision via Label Grouping and Co-Training CVPR 2021 Optimistic Agent: Accurate Graph-Based Value Estimation for More Successful Visual Navigation WACV 2021 Unshuffling Data for Improved Generalization in Visual Question Answering ICCV 2021 Counterfactual Vision and Language Learning CVPR 2020 Counterfactual Vision-and-Language Navigation: Unravelling the Unseen NeurIPS 2020 Gold Seeker: Information Gain From Policy Distributions for Goal-Oriented Vision-and-Langauge Reasoning CVPR 2020 On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law NeurIPS 2020 What's to Know? Uncertainty as a Guide to Asking Goal-Oriented Questions CVPR 2019 DeepSetNet: Predicting Sets With Deep Neural Networks ICCV 2017 Label Filters for Large Scale Multilabel Classification AISTATS 2017 Learning Community-Based Preferences via Dirichlet Process Mixtures of Gaussian Processes IJCAI 2013