Ashwini Pokle

I am a fifth year PhD student at the Machine Learning Department, part of the School of Computer Science at Carnegie Mellon University. I am fortunate to be advised by Prof. Zico Kolter.

Previously, I completed my Master's in Computer Science from Stanford University. During my Master's, I also worked as a Research Assistant at Stanford Vision and Learning Lab (SVL) under supervision of Prof. Silvio Savarese . Prior to joining Stanford, I worked as a Software Development Engineer at Amazon where I was a part of the Prime Video team and Fulfillment Center Technologies team.

I received my Bachelor’s in Computer Science from Birla Institute of Technology and Science, Pilani, India. I have also spent a summer at USC Melady lab where I worked with Prof. Yan Liu.

I have previously interned at FAIR (Meta AI) and Bosch AI.

Email / GitHub / Google Scholar / LinkedIn

Research

I am broadly interested in generative models (diffusion models, flows etc.) and deep equilibrium models (DEQs).

	Training-free Linear Image Inversion via Flows Ashwini Pokle, Matthew J. Muckley, Ricky T. Q. Chen, Brian Karrer Preprint, 2023 arxiv \| We propose a training-free method to solve linear inverse problems using pretrained flow models. Our experiments indicate that images restored via a conditional Optimal transport path, a specific parametrization of flows, are perceptually superior compared to those restored via diffusion paths.
	Deep Equilibrium Based Neural Operators for Steady-State PDEs Tanya Marwah, Ashwini Pokle, J. Zico Kolter, Zachary Chase Lipton, Jianfeng Lu and Andrej Risteski Advances in Neural Information Processing Systems (NeurIPS), 2023 arxiv \| code We demonstrate the benefits of weight-tying as an effective architectural choice for neural operators when applied to steady-state PDEs. We propose FNO-DEQ, a deep equilibrium model based architecture for solving steady-state PDEs that outperforms non-weight tied baselines with 4-6x parameters.
	One-Step Diffusion Distillation via Deep Equilibrium Models Zhengyang Geng, Ashwini Pokle, and J. Zico Kolter Advances in Neural Information Processing Systems (NeurIPS), 2023. An earlier version of this work was also presented at Deployable Generative AI workshop, ICML, 2023 arxiv \| code We propose Generative Equilibrium Transformer (GET), a deep equilibrium model-based variant of Vision Transformer that can efficiently distill sampling chain of diffusion models (EDM) into a single-step generative model.
	Deep Equilibrium Approaches to Diffusion Models Ashwini Pokle, Zhengyang Geng, and J. Zico Kolter Advances in Neural Information Processing Systems (NeurIPS), 2022 arxiv \| code We write the sampling process of DDIM as a deep equilibrium model. This allows us to do fast parallel sampling of DDIM by batching the workload, and enables use of memory efficient O(1) implicit gradients to backprop through the diffusion chain.
	Path independent equilibrium models can better exploit test-time computation Cem Anil, Ashwini Pokle, Kaiqu Liang, Johannes Treutlein, Yuhuai Wu, Shaojie Bai, J. Zico Kolter, and Roger Baker Grosse Advances in Neural Information Processing Systems (NeurIPS)*, 2022 arxiv \| We show that equilibrium models display strong upwards generalization on hard algorithmic tasks when these models converge to the same steady-state behaviour regardless of initialization, a phenomenon we term as “path independence”.
	Contrasting the Landscape of contrastive and non-contrastive learning Ashwini Pokle, Jinjin Tian, Yuchen Li* and Andrej Risteski Conference on Artificial Intelligence and Statistics (AISTATS), 2022 arxiv \| code We show through theoretical results and controlled experiments on simple data models that non-contrastive losses have a preponderance of non-collapsed bad minima. Moreover, we show that the training process does not avoid these minima.
	Visually-Grounded Library of Behaviors for Generalizing Manipulation Across Objects, Configurations and Views Hsiao-Yu Tung, Jingyun Yang, Yunchu Zhang, Gaurav Pathak, Ashwini Pokle, Christopher G. Atkeson, and Katerina Fragkiadaki Conference on Robot Learning (CoRL)*, 2021 arxiv \| code We propose a method for manipulating diverse objects across a wide range of initial and goal configurations and camera placements. We disentangle the standard image-to-action mapping into two separate modules: (1) a behavior selector which selects the behaviors that can successfully perform the desired tasks on the object in hand, and (2) a library of behaviors each of which conditions on extrinsic and abstract object properties to predict actions to execute over time.
	Deep Local Trajectory Planning and Control for Robot Navigation Ashwini Pokle, Roberto Martín-Martín, Patrick Goebel, Vincent Chow, Hans M. Ewald, Junwei Yang, Zhenkai Wang, Amir Sadeghian, Dorsa Sadigh, Silvio Savarese, and Marynel Vázquez IEEE International Conference on Robotics and Automation (ICRA), 2019 arxiv \| We proposed a navigation system that combines ideas from hierarchical planning and machine learning. The system uses a traditional global planner to compute optimal paths towards a goal, and a deep local trajectory planner and velocity controller to compute motion commands.
	Translating Navigation Instructions in Natural Language to a High-Level Plan for Behavioral Robot Navigation Xiaoxue Zang, Ashwini Pokle, Marynel Vázquez, Kevin Chen, Juan Carlos Niebles, Alvaro Soto and Silvio Savarese Conference on Empirical Methods in Natural Language Processing (EMNLP), 2018 arxiv \| code We propose an end-to-end deep learning model for translating free-form natural language instructions to a high-level plan for behavioral robot navigation. The proposed model uses attention mechanisms to connect information from user instructions with a topological representation of the environment.