3 citations · 6 across the 5 of their papers we have counts for
5 papers
Semantic Smoothing for Language Models via Distribution Estimation and Embeddings
Haricharan Balasundaram, Swathi Shree Narashiman, Pranay Mathur +1
We propose semantic smoothing, a smoothing method for language models that uses embeddings to share statistical observations across semantically similar contexts. The starting poin…
Genre Controlled Music Generation via Activation Steering
Swathi Narashiman, Pranay Mathur, Dipanshu Panda +5
Computational Music Generation is evolving towards non-conventional styles, demanding methods that enable precise and controllable blending of diverse music elements. In this work,…
EgoMimic: Scaling Imitation Learning via Egocentric Video
Simar Kareer, Dhruv Patel, Ryan Punamiya +5
The scale and diversity of demonstration data required for imitation learning is a significant challenge. We present EgoMimic, a full-stack framework which scales manipulation via…
Neural Visibility Field for Uncertainty-Driven Active Mapping
Shangjie Xue, Jesse Dill, Pranay Mathur +3
This paper presents Neural Visibility Field (NVF), a novel uncertainty quantification method for Neural Radiance Fields (NeRF) applied to active mapping. Our key insight is that re…
Proactive Human-Robot Interaction using Visuo-Lingual Transformers
Pranay Mathur
Humans possess the innate ability to extract latent visuo-lingual cues to infer context through human interaction. During collaboration, this enables proactive prediction of the un…