Welcome to Yaswanth’s Homepage!

Illustration I am a graduate researcher in AI specializing in Large Language Models. I recently completed my Masters from the Center for Excellence in Artificial Intelligence, Indian Institute of Technology Kharagpur. My research focuses on improving reasoning, planning, and agentic behavior in Language Models, as well as pre-training small language models and optimizing test-time compute inference.

Publications 📚

Research Internships 🧪

Microsoft Logo      UC Berkeley Logo      UIUC Logo      UT Dallas Logo      IIT Kharagpur Logo

News 🏆📚

  • [Apr 2025] Stealth Startup: Currently building my own AI startup in stealth mode. More details coming soon! 🚀
  • [Jun 2024] Independent Consulting: Started freelancing and consulting for startups on AI strategy and implementation. 💼
  • [Apr 2024] Waterloo Research: Started research internship at University of Waterloo’s TIGER Lab with Prof. Wenhu Chen. 🎓
  • [Jul 2024] Publications: Multiple papers accepted at NeurIPS workshops and EMNLP 2024. 📚
  • [Dec 2023] Grant Increase: Microsoft Research doubled our grant to $40,000! 🎉
  • [Oct 2023] Azure A100 Deployment: Launched A100 (80GB GPU) Server on Azure with 220GB RAM. 🚀
  • [Oct 2023] EMNLP 2023: First author paper accepted at EMNLP 2023 (Findings). 🎉
  • [Sep 2023] EMNLP 2023: Served as a Student Paper Reviewer. 🔍
  • [Apr 2023] Best Thesis Awards: Received highest grades for both Bachelor’s and Master’s theses. 🥇
  • [Apr 2023] Best Term Papers: Awarded for “Natural Language Processing”, “Graph Machine Learning”, “AI Design Lab”. 📝

Research Experience

🤖 FinAgent: Financial Trading Agent [Apr 2024 - June 2024]

  • University of Waterloo: Developing a multimodal agent for enhanced financial trading and stock portfolio optimization. Created comprehensive dataset of financial news and stock prices for 100 companies.

📊 Comparing GAN and diffusion-based models for image generation [Feb 2024 - Apr 2024]

  • IIT Kharagpur: Conducted comprehensive experiments to compare Generative Adversarial Networks (GANs) and diffusion-based models for image generation.

📑 Event Extraction using Large Language Models [October 2023 - January 2024]

  • University of Texas, Dallas: Leading a research project focusing on document-level and sentence-level event extraction with GPT-3.5, GPT-4 and various open source Large Language Models.

📚 Citation Integrity [June 2023 - September 2023]

  • University of Illinois at Urbana-Champaign: Developed a new dataset, examined the integrity of citations, and classified them into categories, such as “irrelevant citation,” while also extracting evidence from the cited papers.

🌐 Machine Translation using Large Language Models [May 2023 - September 2023]

  • University of California, Berkeley: Enhanced 500K lines of machine translation data with synthetic generation from LLMs, employing Google-OCR, BERT-based aligners, and Sandhi splitting techniques. Notably increased BLEU scores by 10% using the “No Language Left Behind” (NLLB) model and advanced post-processing methods.

🧩 Nested Compound Parsing and Type Identification [December 2022 - April 2023]

  • Indian Institute of Technology, Kharagpur: Introduced a novel task, dataset and framework focused on identifying correct parsing and semantic relations between components of compounds in Sanskrit.

🧠 Research Interests

  • 🤖 Large Language Models
    • 🧐 Reasoning and Planning
    • 💭 Agentic Behavior
    • 🔍 Pre-training Small Language Models
    • ⚡ Test-Time Compute Inference

🛠️ Technical Skills

  • Languages: Python, C++/C, LaTeX
  • Frameworks/Libraries: PyTorch, Huggingface, LangChain, langgraph, TensorFlow, Gradio, Wandb, Sklearn, NLTK, Streamlit-UI, FastAPI, Mongo, Postgres, Qdrant
  • Tools: Jupyter Notebook, Anaconda, Git, VS Code, Azure, AWS EC2, AWS S3, Google Colab

🚀 Freelance Projects

Since June 2024, I’ve been providing AI consulting services to startups and enterprises, helping them leverage cutting-edge AI technologies to solve complex problems. My freelance work spans across various domains including RAG systems, agentic AI, and specialized model fine-tuning.

Recent Projects:

  • Advanced Autonomous RAG System with User Memory and Vector Store
  • Graph-Based Intelligent Agentic Document RAG
  • Graph-Based ATS System with Advanced LLM Parsing and Ranking Algorithms
  • Dual AI Host Podcast System with Live Audience Interaction Capabilities
  • E-Commerce Product Review Through Summarizing YouTube Videos
  • Perplexity-Inspired Search Engine
  • Agentic System for Intelligent Technical Documentation Generation
  • AI Fashion Model Generation and Virtual Try-On
  • Custom Image Search System for Retail Inventory Management
  • LLM-Based Loan Document Compliance Analysis
  • Specialized Fine-Tuning Pipeline for LLMs and Vision-Language Models
  • Created 30+ AI Agents for Text-To-Action Model

✍️ Blog Posts

🎉 Hobbies & Interests

  • ♟️ Chess Enthusiast: I’m an avid chess player and have won multiple district-level tournaments. Fancy a game? Find me on chess.com and let’s play!
  • 🏀 Basketball & 🏐 Volleyball: Whether it’s shooting hoops or spiking the ball, I love staying active and playing sports in my free time.
  • 👨‍🍳 Cooking & 🌎 Travelling: Exploring new cuisines and cultures is my passion. I find joy in cooking up a storm in the kitchen and embarking on culinary adventures.
  • 🧘‍♂️ Meditation: In the midst of life’s hustle and bustle, I find peace and rejuvenation through meditation. It’s my way of staying grounded and mindful.
  • 🧢 High School Captain: I took on the mantle of leadership in high school, guiding and inspiring my peers as the school captain.