Research publications by Praneeth Vadlapati:

Recent papers

More papers on GitHub

Paper on ShortLang - Compressed Text for efficient LLMs:
https://github.com/Pro-GenAI/ShortLang
Paper on small LLMs for fast and efficient AI:
https://github.com/Pro-GenAI/Small-Specialist-Models
Paper on data classifier for LLM training data:
https://github.com/Pro-GenAI/DataClassifier
Paper on reasoning router to select right reasoning strategy:
https://github.com/Pro-GenAI/Reasoning-Router
Paper on scratchpad-reasoning-in-llms:
https://github.com/Pro-GenAI/S3Q-Reasoning
Latest paper on tool search engine for AI agents:
https://github.com/Pro-GenAI/Tool-SEE

All papers

Title	Paper	GitHub	ResearchGate	Academia	Blog
FAQ-RAG: FAQ-Centric Vector Storage for Trustworthy RAG for QA Tasks Introducing FAQ-RAG, a novel vector storage to enhance the reliability of Retrieval-Augmented Generation (RAG) for question-answering tasks	Paper	Repo	ResearchGate	Academia	Paper page • Scribd • Medium • YouTube
Gen-UI-Lang: A Compact Language for LLM-Driven UI Generation Introducing Gen-UI-Lang, a compact language designed to enable large language models (LLMs) to generate user interfaces (UIs) efficiently and effectively	Paper	Repo	ResearchGate	Academia	Paper page • Scribd • YouTube • Medium • Hugging Face Blog
ToolSEE: Agent Tool Search Engine for Efficient and Scalable Tool Discovery using Retrieval Introducing ToolSEE, an AI agent tool search engine for reliable tool selection based on contextual relevance and performance metrics	Paper	Repo	ResearchGate	Academia	Paper page • Medium • Scribd • Hugging Face Blog • YouTube
Index-RAG: Storing Text Location in Vector Databases for QA tasks Introducing Index-RAG, a novel method to enhance retrieval-augmented generation by storing text location in vector databases for improved question-answering tasks	Paper	Repo	ResearchGate	Academia	Paper page • Scribd • YouTube
ShortLang: Compressed Text for efficient LLMs Introducing ShortLang, a novel compressed text format to optimize LLM performance and reduce costs	Paper	Repo	ResearchGate	Academia	Paper page • Scribd • YouTube
Small Specialist Models: A Team of Cost-Effective, Efficient, and Fast AI models Exploring the potential of small language models in AI	Paper	Repo	ResearchGate	Academia	Paper page • Scribd • YouTube
Data Classifier: An AI-driven approach to Label LLM Training Data AI-based data classification for LLM training data	Paper	Repo	ResearchGate	Academia	Paper page • Scribd • YouTube
Reasoning Router: Dynamic Multi-Strategy Reasoning for Robust Multi-Step Problem Solving Router to select optimal reasoning strategy for LLMs	Paper	Repo	ResearchGate	Academia	Paper page • Scribd • YouTube
Scratchpad 3Q Reasoning: Surfacing Assumptions to Mitigate Hallucination and Improve Truthfulness in Large Language Models Exploring the use of scratchpads in LLMs for improved reasoning	Paper	Repo	ResearchGate	Academia	Paper page • Scribd • YouTube
MCP Agent Action Guard: Safe AI Agents through Action Classifier Classifying AI agent actions to categorize them for safety and reliability	Paper	Repo	ResearchGate	Academia	Medium • Paper page • Scribd • Hugging Face Blog • YouTube
iRAT: Replanning and Controlled Retrieval for Robust LLM Reasoning Retrieval-augmented reasoning techniques for LLMs	Paper	Repo	ResearchGate	Academia	Medium • Paper page • Scribd • YouTube
AutoTrendyKeywords: Real-Time AI-Driven Trend-Based SEO Using LLMs Real-time trend detection for SEO with LLMs	Paper	Repo	ResearchGate	Academia	Medium • Paper page
LML-DAP: Language Model Learning a Dataset for Data-Augmented Prediction Combining language models with structured data for better predictions	Paper	Repo	ResearchGate	Academia	arXiv • Medium • HF article
UpdAgent: AI Agent Version Control Framework for Real-Time Updation of Tools Version control for agent tooling	Paper	Repo	ResearchGate	Academia
AGIent and Tool-Mart: A Super-Agent Framework Enabled by Marketplace-Driven Tool Selection Super-agent architecture with a tools marketplace	Paper	Repo	ResearchGate	Academia
AutoPureData: Automated Filtering of Undesirable Web Data to Update LLM Knowledge Automated filtering pipeline for LLM dataset hygiene	Paper	Repo	ResearchGate	Academia	arXiv • Paper page • HF article • Scribd
AutoWatcher: A Real-Time Context-Aware Security Alert System using LLMs Security alerting with LLMs	Paper	Repo	ResearchGate	Academia
The Power of Roles: Investigating Impact of Three Message Types on LLM Responses Study of message types and system/user/assistant roles	Paper	Repo	ResearchGate	Academia
AutoPrecisePrompts: Automated LLM-based Prompt Engineering for Structured Data Processing Automated prompt engineering for tabular/structured data	Paper	Repo	ResearchGate	Academia	Medium
Agent-Supervisor: Supervising Actions of Autonomous AI Agents to Ensure Ethical Compliance Supervisor framework to ensure ethical agent behaviour	Paper	Repo	ResearchGate	Academia	Paper page • Scribd
Hierarchical Management of AI for Automated Monitoring and Query Resolution Hierarchical AI architecture for monitoring and automated resolution	Paper	Repo	ResearchGate	Academia	Paper page • Scribd
Does Seed Matter? Investigating the Effect of Random Seeds on LLM Accuracy Study on random seed effects in LLM evaluations	Paper	Repo	ResearchGate	Academia
Investigating the Impact of Linguistic Errors of Prompts on LLM Accuracy Effects of prompt linguistic errors on model accuracy	Paper	Repo	ResearchGate	Academia
iSearch: Enhanced Intelligent Search Based on a Query using LLMs LLM-enhanced intelligent search	Paper	Repo	ResearchGate	Academia
Multilingual Prompting in LLMs: Investigating the Accuracy and Performance Multilingual prompting study	Paper	Repo	ResearchGate	Academia
EaseText: Enhancing Comprehension of Complex Sentences using LLMs Improving comprehension of complex text using LLMs	Paper	Repo	ResearchGate	Academia
AutoMarineWatcher: Real-Time Maritime Surveillance to Detect Threats using YOLO Maritime surveillance using YOLO	Paper	Repo	ResearchGate	Academia
TokEncryption: Enhanced Hashing of Text using Tokenization Tokenization-based text hashing	Paper	Repo	ResearchGate	Academia
TokenizedDB: Text Tokenization using NLP for Enhanced Storage Efficiency and Data Privacy Tokenization for storage efficiency and privacy	Paper	Repo	ResearchGate	Academia
TokChat: Tokenization of Text for Secured Peer-to-Peer Communication Secure P2P communication using tokenization	Paper	Repo	ResearchGate	Academia
Tokenization Beyond NLP: Potential Applications in Data Analytics, Cybersecurity, and Beyond Exploration of tokenization applications outside traditional NLP use-cases	Paper		ResearchGate	Academia
Memory Transformers: Neural Memory Banks for Textual Memory Introducing Neural Memory Transformers, a novel architecture that combines transformer models with neural memory banks for enhanced textual memory and retrieval	Paper	Repo	ResearchGate	Academia	Paper page • Scribd

Website:
https://prane-eth.github.io/
YouTube Playlist:
https://www.youtube.com/playlist?list=PLFPzYi1b0ClIDZ59f3V4Wd9QEiDvnavNZ

Work featured:
https://quantumzeitgeist.com/ai-powered-surveillance-enhancing-public-safety-with-multimodal-large-language-models/
https://www.alphaxiv.org/overview/2409.18957
Sciety - paper 1
Sciety - paper 2
Sciety - paper 3
Sciety Labs - paper 4
Sciety Labs - paper 5
Bohrium - LML-DAP
ChatPaper - paper 1
GoatStack - LML-DAP
PromptLayer - AutoPureData
PaperReading Club - paper 1