Panwar, Madhur

8 publications

NeurIPS 2025 For Better or for Worse, Transformers Seek Patterns for Memorization Madhur Panwar, Gail Weiss, Navin Goyal, Antoine Bosselut

ICLR 2024 In-Context Learning Through the Bayesian Prism Madhur Panwar, Kabir Ahuja, Navin Goyal

NeurIPS 2024 InversionView: A General-Purpose Method for Reading Information from Neural Activations Xinting Huang, Madhur Panwar, Navin Goyal, Michael Hahn

ICMLW 2024 InversionView: A General-Purpose Method for Reading Information from Neural Activations Xinting Huang, Madhur Panwar, Navin Goyal, Michael Hahn

ICMLW 2024 Learning Syntax Without Planting Trees: Understanding When and Why Transformers Generalize Hierarchically Kabir Ahuja, Vidhisha Balachandran, Madhur Panwar, Tianxing He, Noah A. Smith, Navin Goyal, Yulia Tsvetkov

NeurIPSW 2023 In-Context Learning and Bayesian Inference Madhur Panwar, Kabir Ahuja, Navin Goyal

NeurIPSW 2023 Surprising Deviations from Bayesian View in In-Context Learning Madhur Panwar, Kabir Ahuja, Navin Goyal

NeurIPSW 2023 Transformers Can Learn to Solve Linear-Inverse Problems In-Context Kabir Ahuja, Madhur Panwar, Navin Goyal