Bhavya Kailkhura

STAR-1: Safer Alignment of Reasoning LLMs with 1K Data AAAI 2026 ELFS: Label-Free Coreset Selection with Proxy Training Dynamics ICLR 2025 Extracting and Understanding the Superficial Knowledge in Alignment NAACL 2025 GRNFormer: A Biologically-Guided Framework for Integrating Gene Regulatory Networks into RNA Foundation Models ACL 2025 Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense NAACL 2025 Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion NAACL 2025 TruthPrInt: Mitigating Large Vision-Language Models Object Hallucination Via Latent Truthful-Guided Pre-Intervention ICCV 2025 Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies ICML 2024 Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression ICML 2024 DeepZero: Scaling Up Zeroth-Order Optimization for Deep Model Training ICLR 2024 GTBench: Uncovering the Strategic Reasoning Capabilities of LLMs via Game-Theoretic Evaluations NeurIPS 2024 Leveraging Hierarchical Feature Sharing for Efficient Dataset Condensation ECCV 2024 NEFTune: Noisy Embeddings Improve Instruction Finetuning ICLR 2024 On the Fly Neural Style Smoothing for Risk-Averse Domain Generalization WACV 2024 Position: TrustLLM: Trustworthiness in Large Language Models ICML 2024 RankMean: Module-Level Importance Score for Merging Fine-tuned LLM Models ACL 2024 ReTA: Recursively Thinking Ahead to Improve the Strategic Reasoning of Large Language Models NAACL 2024 Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models ACL 2024 SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning EMNLP 2024 Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis NeurIPS 2024 Transformers Can Do Arithmetic with the Right Embeddings NeurIPS 2024 Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities JMLR 2023 Improving Diversity With Adversarially Learned Transformations for Domain Generalization WACV 2023 Neural Image Compression: Generalization, Robustness, and Spectral Biases NeurIPS 2023 A Spectral View of Randomized Smoothing under Common Corruptions: Benchmarking and Improving Certified Robustness ECCV 2022 COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks ICLR 2022 Models Out of Line: A Fourier Lens on Distribution Shift Robustness NeurIPS 2022 On the Certified Robustness for Ensemble Models and Beyond ICLR 2022 Attribute-Guided Adversarial Training for Robustness to Natural Perturbations AAAI 2021 A Winning Hand: Compressing Deep Networks Can Improve Out-of-Distribution Robustness NeurIPS 2021 Can Shape Structure Features Improve Model Robustness Under Diverse Adversarial Settings? ICCV 2021 Deep kernels with probabilistic embeddings for small-data learning UAI 2021 G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of Teacher Discriminators NeurIPS 2021 How Robust Are Randomized Smoothing Based Defenses to Data Poisoning? CVPR 2021 Multi-Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted Network ICLR 2021 Scalability vs. Utility: Do We Have To Sacrifice One for the Other in Data Importance Quantification? CVPR 2021 Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning NeurIPS 2021 Adversarial Mutual Information for Text Generation ICML 2020 A Statistical Mechanics Framework for Task-Agnostic Sample Design in Machine Learning NeurIPS 2020 Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond NeurIPS 2020 Mix-n-Match : Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learning ICML 2020 On the Design of Black-Box Adversarial Examples by Leveraging Gradient-Free Optimization and Operator Splitting Method ICCV 2019 A Spectral Approach for the Design of Experiments: Design, Analysis and Algorithms JMLR 2018 Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization NeurIPS 2018