4 papers
Why DDIM Hallucinates More Than DDPM: A Theoretical Analysis of Reverse Dynamics
Muhammad H. Ashiq, Samanyu Arora, Abhinav N. Harish +3
We theoretically study the hallucination phenomena in two canonical diffusion samplers: the stochastic Denoising Diffusion Probabilistic Model (DDPM) and the deterministic Denoisin…
Reinforcement Learning Within the Classical Robotics Stack: A Case Study in Robot Soccer
Adam Labiosa, Zhihan Wang, Siddhant Agarwal +10
Robot decision-making in partially observable, real-time, dynamic, and multi-agent environments remains a difficult and unsolved challenge. Model-free reinforcement learning (RL) i…
Reinforcement Learning via Auxiliary Task Distillation
Abhinav Narayan Harish, Larry Heck, Josiah P. Hanna +2
We present Reinforcement Learning via Auxiliary Task Distillation (AuxDistill), a new method that enables reinforcement learning (RL) to perform long-horizon robot control problems…
A Graph Neural Network Approach for Temporal Mesh Blending and Correspondence
Aalok Gangopadhyay, Abhinav Narayan Harish, Prajwal Singh +1
We have proposed a self-supervised deep learning framework for solving the mesh blending problem in scenarios where the meshes are not in correspondence. To solve this problem, we…