Suraj Srinivas

51 papers A* 10A 4B 1Journal 30Unranked 5

Year	Rank	Type	Title / Venue / Authors
2026	—	`conf`	Evaluating Adversarial Robustness of Concept Representations in Sparse Autoencoders. EACL (Volume 1: Long Papers) Aaron J. Li, Suraj Srinivas, Usha Bhalla, Himabindu Lakkaraju
2025	A*	`conf`	How Much Can We Forget about Data Contamination? ICML Sebastian Bordt, Suraj Srinivas, Valentyn Boreiko, Ulrike von Luxburg
2025	J	`jnl`	Interpretability Illusions with Sparse Autoencoders: Evaluating Robustness of Concept Representations. CoRR Aaron J. Li, Suraj Srinivas, Usha Bhalla, Himabindu Lakkaraju
2025	J	`jnl`	Towards Interpretable Soft Prompts. CoRR Oam Patel, Jason Wang, Nikhil Shivakumar Nayak, Suraj Srinivas, Himabindu Lakkaraju
2024	J	`jnl`	All Roads Lead to Rome? Exploring Representational Similarities Between Latent Spaces of Generative Image Models. CoRR Charumathi Badrinath, Usha Bhalla, Alex Oesterling, Suraj Srinivas, Himabindu Lakkaraju
2024	A	`conf`	Characterizing Data Point Vulnerability as Average-Case Robustness. UAI Tessa Han, Suraj Srinivas, Himabindu Lakkaraju
2024	J	`jnl`	Generalized Group Data Attribution. CoRR Dan Ley, Suraj Srinivas, Shichang Zhang, Gili Rusak, Himabindu Lakkaraju
2024	J	`jnl`	How much can we forget about Data Contamination? CoRR Sebastian Bordt, Suraj Srinivas, Valentyn Boreiko, Ulrike von Luxburg
2024	A*	`conf`	Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE). NeurIPS Usha Bhalla, Alex Oesterling, Suraj Srinivas, Flávio P. Calmon, Himabindu Lakkaraju
2024	J	`jnl`	Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE). CoRR Usha Bhalla, Alex Oesterling, Suraj Srinivas, Flávio P. Calmon, Himabindu Lakkaraju
2024	J	`jnl`	Towards Unifying Interpretability and Control: Evaluation via Intervention. CoRR Usha Bhalla, Suraj Srinivas, Asma Ghandeharioun, Himabindu Lakkaraju
2023	J	`jnl`	Certifying LLM Safety against Adversarial Prompting. CoRR Aounon Kumar, Chirag Agarwal, Suraj Srinivas, Soheil Feizi, Hima Lakkaraju
2023	J	`jnl`	Consistent Explanations in the Face of Model Indeterminacy via Ensembling. CoRR Dan Ley, Leonard Tang, Matthew Nazari, Hongjin Lin, Suraj Srinivas, Himabindu Lakkaraju
2023	A*	`conf`	Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretability. NeurIPS Usha Bhalla, Suraj Srinivas, Himabindu Lakkaraju
2023	J	`jnl`	Efficient Estimation of the Local Robustness of Machine Learning Models. CoRR Tessa Han, Suraj Srinivas, Himabindu Lakkaraju
2023	A	`conf`	On Minimizing the Impact of Dataset Shifts on Actionable Explanations. UAI Anna P. Meyer, Dan Ley, Suraj Srinivas, Himabindu Lakkaraju
2023	J	`jnl`	On Minimizing the Impact of Dataset Shifts on Actionable Explanations. CoRR Anna P. Meyer, Dan Ley, Suraj Srinivas, Himabindu Lakkaraju
2023	J	`jnl`	Verifiable Feature Attributions: A Bridge between Post Hoc Explainability and Inherent Interpretability. CoRR Usha Bhalla, Suraj Srinivas, Himabindu Lakkaraju
2023	A*	`conf`	Which Models have Perceptually-Aligned Gradients? An Explanation via Off-Manifold Robustness. NeurIPS Suraj Srinivas, Sebastian Bordt, Himabindu Lakkaraju
2023	J	`jnl`	Which Models have Perceptually-Aligned Gradients? An Explanation via Off-Manifold Robustness. CoRR Suraj Srinivas, Sebastian Bordt, Hima Lakkaraju
2023	J	`jnl`	Word-Level Explanations for Analyzing Bias in Text-to-Image Models. CoRR Alexander Lin, Lucas Monteiro Paes, Sree Harsha Tanneru, Suraj Srinivas, Himabindu Lakkaraju
2022	—	`conf`	Cyclical Pruning for Sparse Neural Networks. CVPR Workshops Suraj Srinivas, Andrey Kuzmin, Markus Nagel, Mart van Baalen, Andrii Skliar, Tijmen Blankevoort
2022	J	`jnl`	Cyclical Pruning for Sparse Neural Networks. CoRR Suraj Srinivas, Andrey Kuzmin, Markus Nagel, Mart van Baalen, Andrii Skliar, Tijmen Blankevoort
2022	A*	`conf`	Data-Efficient Structured Pruning via Submodular Optimization. NeurIPS Marwa El Halabi, Suraj Srinivas, Simon Lacoste-Julien
2022	J	`jnl`	Data-Efficient Structured Pruning via Submodular Optimization. CoRR Marwa El Halabi, Suraj Srinivas, Simon Lacoste-Julien
2022	A*	`conf`	Efficient Training of Low-Curvature Neural Networks. NeurIPS Suraj Srinivas, Kyle Matoba, Himabindu Lakkaraju, François Fleuret
2022	J	`jnl`	Flatten the Curve: Efficiently Training Low-Curvature Neural Networks. CoRR Suraj Srinivas, Kyle Matoba, Himabindu Lakkaraju, François Fleuret
2022	A*	`conf`	Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanations. NeurIPS Tessa Han, Suraj Srinivas, Himabindu Lakkaraju
2022	J	`jnl`	Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post hoc Explanations. CoRR Tessa Han, Suraj Srinivas, Himabindu Lakkaraju
2021	A*	`conf`	Rethinking the Role of Gradient-based Attribution Methods for Model Interpretability. ICLR Suraj Srinivas, François Fleuret
2020	J	`jnl`	Gradient Alignment in Deep Neural Networks. CoRR Suraj Srinivas, François Fleuret
2019	A*	`conf`	Full-Gradient Representation for Neural Network Visualization. NeurIPS Suraj Srinivas, François Fleuret
2019	J	`jnl`	Full-Jacobian Representation of Neural Networks. CoRR Suraj Srinivas, François Fleuret
2018	—	`conf`	Estimating Confidence for Deep Neural Networks through Density modeling. SPCOM Akshayvarun Subramanya, Suraj Srinivas, R. Venkatesh Babu
2018	A*	`conf`	Knowledge Transfer with Jacobian Matching. ICML Suraj Srinivas, François Fleuret
2018	J	`jnl`	Knowledge Transfer with Jacobian Matching. CoRR Suraj Srinivas, François Fleuret
2017	—	`ch.`	An Introduction to Deep Convolutional Neural Nets for Computer Vision. Deep Learning for Medical Image Analysis Suraj Srinivas, Ravi Kiran Sarvadevabhatla, Konda Reddy Mopuri, Nikita Prabhu, Srinivas S. S. Kruthiventi, R. Venkatesh Babu
2017	J	`jnl`	Confidence estimation in Deep Neural networks via density modelling. CoRR Akshayvarun Subramanya, Suraj Srinivas, R. Venkatesh Babu
2017	—	`conf`	Training Sparse Neural Networks. CVPR Workshops Suraj Srinivas, Akshayvarun Subramanya, R. Venkatesh Babu
2016	J	`jnl`	A Taxonomy of Deep Convolutional Neural Nets for Computer Vision. CoRR Suraj Srinivas, Ravi Kiran Sarvadevabhatla, Konda Reddy Mopuri, Nikita Prabhu, Srinivas S. S. Kruthiventi, R. Venkatesh Babu
2016	J	`jnl`	Compensating for Large In-Plane Rotations in Natural Images. CoRR Lokesh Boominathan, Suraj Srinivas, R. Venkatesh Babu
2016	—	`conf`	Compensating for large in-plane rotations in natural images. ICVGIP Lokesh Boominathan, Suraj Srinivas, R. Venkatesh Babu
2016	J	`jnl`	Generalized Dropout. CoRR Suraj Srinivas, R. Venkatesh Babu
2016	A	`conf`	Learning Neural Network Architectures using Backpropagation. BMVC Suraj Srinivas, Radhakrishnan Venkatesh Babu
2016	J	`jnl`	Training Sparse Neural Networks. CoRR Suraj Srinivas, Akshayvarun Subramanya, R. Venkatesh Babu
2015	J	`jnl`	A Taxonomy of Deep Convolutional Neural Nets for Computer Vision. Frontiers Robotics AI Suraj Srinivas, Ravi Kiran Sarvadevabhatla, Konda Reddy Mopuri, Nikita Prabhu, Srinivas S. S. Kruthiventi, R. Venkatesh Babu
2015	A	`conf`	Data-free Parameter Pruning for Deep Neural Networks. BMVC Suraj Srinivas, R. Venkatesh Babu
2015	J	`jnl`	Data-free parameter pruning for Deep Neural Networks. CoRR Suraj Srinivas, R. Venkatesh Babu
2015	J	`jnl`	Learning the Architecture of Deep Neural Networks. CoRR Suraj Srinivas, R. Venkatesh Babu
2014	B	`conf`	Controlled blurring for improving image reconstruction quality in flutter-shutter acquisition. ICIP Suraj Srinivas, Aniruddha Adiga, Chandra Sekhar Seelamantula
2014	J	`jnl`	Universal Gestural Remote: A Conceptual Framework for a Human-Device Interface. Aust. J. Intell. Inf. Process. Syst. Suraj Srinivas, Naman Nandan, Preetham Kulai, Akash R. Vasishta