Skip to content
View AnkitXP's full-sized avatar
  • Texas A&M University
  • College Station, TX
  • 19:39 (UTC -06:00)
  • LinkedIn in/ankitbasu

Block or report AnkitXP

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
AnkitXP/README.md

💫 Howdy, I'm Ankit!

  • I’m a graduate student at Texas A&M University, College Station.
  • Passionate about Natural Language Processing (NLP), Large Language Models (LLMs), AI Agents and Reinforcement Learning (RL).
  • My research and projects focus on:
    • Reasoning and Self-Correction Abilities of Large Language Models
    • Alignment of LLMs using Reinforcement Learning
    • Fine-tuning LLMs to instill better domain knowledge
    • Developing intelligent AI agents capable of using external tools and knowledge to generate more accurate responses
  • With a solid foundation in Machine Learning, Deep Learning, and Data Science, I am enthusiastic about solving complex business problems and making impactful contributions through innovative AI solutions.

💻 Tech Stack:

AI / ML:

Python PyTorch scikit-learn OpenCV Pandas NumPy Matplotlib

Generative AI / LLMs:

HuggingFace LangChain ChromaDB OpenAI LlamaIndex Streamlit

Data Analysis / Visualization:

Tableau Google Data Studio Oracle PostgreSQL MySQL

Platform / Source Control:

Git Docker

🌐 Connect with me:

LinkedIn GMAIL

Pinned Loading

  1. RL-SCoRe RL-SCoRe Public

    A Reinforcement Learning based inference-time reflection and self-correction framework to rectify errors without external agents or knowledge distillation.

    Python 1 1

  2. RLHF-PPO RLHF-PPO Public

    RLHF (Reinforcement Learning from Human Feedback) with PPO (Proximal Policy Optimization) is a reinforcement learning method where a model is fine-tuned using human feedback, optimized through PPO …

    Python

  3. CCT-ViT CCT-ViT Public

    A Compact Convolution Transformer is a neural network architecture that combines the efficiency of convolutional layers with the long-range dependency modeling capabilities of transformers, designe…

    Python

  4. Multimodal-Fusion-Model Multimodal-Fusion-Model Public

    An architecture capable of taking different types inputs (images and sound) and fuse the models to build a multimodal classifier.

    Python

  5. FashionMNIST-Classification FashionMNIST-Classification Public

    Forked from archit28-tamu/fashion_mnist_project

    End-to-end image classification with conventional machine learning and deep learning models.

    Jupyter Notebook

  6. PDF-Insight PDF-Insight Public

    PDF Insight is an interactive chatbot application that allows users to upload PDF documents and engage in natural language conversations about their content.

    Python