4 papers
Thinking Ahead: Prospection-Guided Retrieval of Memory with Language Models
Harshita Chopra, Krishna Kant Chintalapudi, Suman Nath +2
Long-horizon personalization requires dialogue assistants to retrieve user-specific facts from extended interaction histories. In practice, many relevant facts often have low seman…
How Many Parameters Does Your Task Really Need? Task Specific Pruning with LLM-Sieve
Waleed Reda, Abhinav Jangda, Krishna Chintalapudi
As Large Language Models (LLMs) are increasingly deployed for narrow tasks in resource-constrained settings, a central question arises: how much of an LLM is truly necessary for a…
MCAL: Minimum Cost Human-Machine Active Labeling
Hang Qiu, Krishna Chintalapudi, Ramesh Govindan
Today, ground-truth generation uses data sets annotated by cloud-based annotation services. These services rely on human annotation, which can be prohibitively expensive. In this p…
Satyam: Democratizing Groundtruth for Machine Vision
Hang Qiu, Krishna Chintalapudi, Ramesh Govindan
The democratization of machine learning (ML) has led to ML-based machine vision systems for autonomous driving, traffic monitoring, and video surveillance. However, true democratiz…