I am Saaket Agashe, a Ph.D student at the University of California, Santa Cruz where I work with Prof. Xin Eric Wang. My research interests lie in the intersection of NLP, Embodied AI, and Human-AI Collaboration. My research goal is to develop agents and systems that can co-exist and collaborate with humans in a shared environment. Currently, I am exploring the use of Foundation Models (LLMs, LVLMs) for multi-agent coordination.
Previously, as a Master's student at UCSC, I worked on Language Grounding and Vision and Language Navigation.
I graduated with a B.Tech in Electronics Engineering from VJTI, Mumbai, India in 2020, where I focused on Robotics.
For more details, check my CV or drop me an email.
Research
LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models
, Yue Fan, Anthony Reyna, Xin Eric Wang
Description: Introduced the LLM-Coordination Benchmark and conducted a comprehensive analysis of LLMs in Pure Coordination Games.
Website
Paper
Code
Localization using Spatial Descriptions
, Xin Eric Wang
Description: Visually grounding Spatial Descriptions to a single point in an image based on descriptions of objects in the neighborhood of the point.
Code
Interacting with Next-Phrase Suggestions: How Suggestion Systems Aid and Influence the Cognitive Processes of Writing
Advait Bhat, , Niharika Mohile, Parth Oberoi, Ravi Jangir, Anirudha Joshi
Best Paper Honourable Mention @ IUI’23
Description: Exploratory qualitative study to understand how writers interact with next-phrase suggestions.
Code
Paper
How do people interact with biased text prediction models while writing?
Advait Bhat, , Anirudha Joshi
First HCI+NLP Workshop @ EACL 2021
Description: Pilot study to understand how people interact with next phrase suggestion system.
Code
Paper
Perception and Motion Planning for Autonomous mobile manipulator
, Akshay Paralikar, Shweta Kumaran, Shambhavi Kuthe, Aditya Gawali, Hiten Kothari, Shashank Deshmukh, Faruk Kazi
Description: Develop a functional autonomous mobile manipulator for testing algorithms
developed in simulation in the real world.
Code