Kokhlikyan, Narine

10 publications

ICLR 2026 CIMemories: A Compositional Benchmark for Contextual Integrity in LLMs Niloofar Mireshghallah, Neal Mangaokar, Narine Kokhlikyan, Arman Zharmagambetov, Manzil Zaheer, Saeed Mahloujifar, Kamalika Chaudhuri

ICLR 2026 Hallucination Reduction with CASAL: Contrastive Activation Steering for Amortized Learning Wannan Yang, Xinchi Qiu, Lei Yu, Yuchen Zhang, Aobo Yang, Narine Kokhlikyan, Nicola Cancedda, Diego Garcia-Olano

ICLRW 2025 On Symmetries in Convolutional Weights Bilal Alsallakh, Timothy J Wroge, Vivek Miglani, Narine Kokhlikyan

NeurIPS 2024 Measuring Dejavu Memorization Efficiently Narine Kokhlikyan, Bargav Jayaraman, Florian Bordes, Chuan Guo, Kamalika Chaudhuri

NeurIPS 2023 Error Discovery by Clustering Influence Embeddings Fulton Wang, Julius Adebayo, Sarah Tan, Diego Garcia-Olano, Narine Kokhlikyan

ICLRW 2023 Error Discovery by Clustering Influence Embeddings Fulton Wang, Julius Adebayo, Sarah Tan, Diego Garcia-Olano, Narine Kokhlikyan

ICLR 2023 Mind the Pool: Convolutional Neural Networks Can Overfit Input Size Bilal Alsallakh, David Yan, Narine Kokhlikyan, Vivek Miglani, Orion Reblitz-Richardson, Pamela Bhattacharya

NeurIPSW 2021 Are Convolutional Networks Inherently Foveated? Bilal Alsallakh, Vivek Miglani, Narine Kokhlikyan, David Adkins, Orion Reblitz-Richardson

NeurIPSW 2021 Debugging the Internals of Convolutional Networks Bilal Alsallakh, Narine Kokhlikyan, Vivek Miglani, Shubham Muttepawar, Edward Wang, Sara Zhang, David Adkins, Orion Reblitz-Richardson

ICLR 2021 Mind the Pad -- CNNs Can Develop Blind Spots Bilal Alsallakh, Narine Kokhlikyan, Vivek Miglani, Jun Yuan, Orion Reblitz-Richardson