5 papers
SalesRLAgent: A Reinforcement Learning Approach for Real-Time Sales Conversion Prediction and Optimization
Nandakishor M
Current approaches to sales conversation analysis and conversion prediction typically rely on Large Language Models (LLMs) combined with basic retrieval augmented generation (RAG).…
ForcePose: A Deep Learning Approach for Force Calculation Based on Action Recognition Using MediaPipe Pose Estimation Combined with Object Detection
Nandakishor M, Vrinda Govind, Anuradha Puthalath +8
Force estimation in human-object interactions is crucial for various fields like ergonomics, physical therapy, and sports science. Traditional methods depend on specialized equipme…
DeepRAG: Building a Custom Hindi Embedding Model for Retrieval Augmented Generation from Scratch
Nandakishor M
In this paper, I present our work on DeepRAG, a specialized embedding model we built specifically for Hindi language in RAG systems. While LLMs have gotten really good at generatin…
Continuous Learning Conversational AI: A Personalized Agent Framework via A2C Reinforcement Learning
Nandakishor M, Anjali M
Creating personalized and adaptable conversational AI remains a key challenge. This paper introduces a Continuous Learning Conversational AI (CLCA) approach, implemented using A2C…
High-Accuracy ECG Image Interpretation using Parameter-Efficient LoRA Fine-Tuning with Multimodal LLaMA 3.2
Nandakishor M, Anjali M
Electrocardiogram (ECG) interpretation is a cornerstone of cardiac diagnostics. This paper explores a practical approach to enhance ECG image interpretation using the multimodal LL…