Balasubramanian, Sriram

9 publications

TMLR 2025 Can AI-Generated Text Be Reliably Detected? Stress Testing AI Text Detectors Under Various Attacks Vinu Sankar Sadasivan, Aounon Kumar, Sriram Balasubramanian, Wenxiao Wang, Soheil Feizi

ICLR 2025 Rethinking Artistic Copyright Infringements in the Era of Text-to-Image Generative Models Mazda Moayeri, Sriram Balasubramanian, Samyadeep Basu, Priyatham Kattakinda, Atoosa Chegini, Robert Brauneis, Soheil Feizi

ICLRW 2025 SpurLens: Finding Spurious Correlations in Multimodal LLMs Parsa Hosseini, Sumit Nawathe, Mazda Moayeri, Sriram Balasubramanian, Soheil Feizi

NeurIPS 2024 Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP Sriram Balasubramanian, Samyadeep Basu, Soheil Feizi

ICMLW 2024 Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP Sriram Balasubramanian, Samyadeep Basu, Soheil Feizi

NeurIPSW 2024 Rethinking Artistic Copyright Infringements in the Era of Text-to-Image Generative Models Mazda Moayeri, Samyadeep Basu, Sriram Balasubramanian, Priyatham Kattakinda, Atoosa Chegini, Robert Brauneis, Soheil Feizi

NeurIPS 2023 Exploring Geometry of Blind Spots in Vision Models Sriram Balasubramanian, Gaurang Sriramanan, Vinu Sankar Sadasivan, Soheil Feizi

AAAI 2023 Simulating Network Paths with Recurrent Buffering Units Divyam Anshumaan, Sriram Balasubramanian, Shubham Tiwari, Nagarajan Natarajan, Sundararajan Sellamanickam, Venkat N. Padmanabhan

ICCV 2023 Towards Improved Input Masking for Convolutional Neural Networks Sriram Balasubramanian, Soheil Feizi