38 citations · 48 across the 7 of their papers we have counts for
8 papers
Tracking Representation Dynamics in Large Language Models with Persistent Homology
Naman Malhotra, Jay Ambadkar, Abhinav Gupta +4
Large language models are commonly aligned through supervised fine-tuning, yet little is known about how their internal representations evolve during this process. We study alignme…
ArK: Augmented Reality with Knowledge Interactive Emergent Ability
Qiuyuan Huang, Jae Sung Park, Abhinav Gupta +8
Despite the growing adoption of mixed reality and interactive AI agents, it remains challenging for these systems to generate high quality 2D/3D scenes in unseen environments. The…
Dynamic population-based meta-learning for multi-agent communication with natural language
Abhinav Gupta, Marc Lanctot, Angeliki Lazaridou
In this work, our goal is to train agents that can coordinate with seen, unseen as well as human partners in a multi-agent communication environment involving natural language. Pre…
Learning Multi-Objective Curricula for Robotic Policy Learning
Jikun Kang, Miao Liu, Abhinav Gupta +3
Various automatic curriculum learning (ACL) methods have been proposed to improve the sample efficiency and final performance of deep reinforcement learning (DRL). They are designe…
Towards Graph Representation Learning in Emergent Communication
Agnieszka Słowik, Abhinav Gupta, William L. Hamilton +2
Recent findings in neuroscience suggest that the human brain represents information in a geometric structure (for instance, through conceptual spaces). In order to communicate, we…
Capacity, Bandwidth, and Compositionality in Emergent Language Learning
Cinjon Resnick, Abhinav Gupta, Jakob Foerster +2
Many recent works have discussed the propensity, or lack thereof, for emergent languages to exhibit properties of natural languages. A favorite in the literature is learning compos…
Sentiment Classification using Images and Label Embeddings
Laura Graesser, Abhinav Gupta, Lakshay Sharma +1
In this project we analysed how much semantic information images carry, and how much value image data can add to sentiment analysis of the text associated with the images. To bette…
Visual Features for Context-Aware Speech Recognition
Abhinav Gupta, Yajie Miao, Leonardo Neves +1
Automatic transcriptions of consumer-generated multi-media content such as "Youtube" videos still exhibit high word error rates. Such data typically occupies a very broad domain, h…