Skip to content
View shotsan's full-sized avatar
9 followers · 27 following
  • 22:23 (UTC -12:00)

Block or report shotsan

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
shotsan/readme.md

✋ I'm Santosh.

I have PhD in Network Control, and Learning from Texas A&M university under Dr. P. R. Kumar

Current Research Interests

  1. Applying Machine Learning to large scale problems
  2. Training Neural Nets and Large Language Models

I was TA for ECEN 740 Machine Learning '22 and '24, Primary ML course at Texas A&M Electrical and Computer Engineering.

I specialize in designing, building, and deploying plug-and-play intelligent systems.

I built Real-Time Voice agents for Learning, Try it out My recent endevours include working full-time contributing to web agents: Amazon Buy For Me Worked on web maniputions to benefit agents, scraping for right selectors, addressing challenges in security, inference, and post-training of vision grounding models.

Occasionally developing general navigation and control policies of my Unitree Go 2, and AR4 6DOF robot




Pinned Loading

  1. agentic-browser agentic-browser Public

    Simple Agentic Browser to validate model performance

    Python

  2. Double-Descent-of-Neural-Networks Double-Descent-of-Neural-Networks Public

    Double Descent of Neural Networks

    Jupyter Notebook

  3. gpt-fast gpt-fast Public

    Forked from meta-pytorch/gpt-fast

    Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

    Python

  4. attention_mechanims attention_mechanims Public

    Forked from facebookresearch/xformers

    Hackable and optimized Transformers building blocks, supporting a composable construction.

    Python

  5. AppAgent AppAgent Public

    Forked from TencentQQGYLab/AppAgent

    AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.

    Python

  6. GLM-130B GLM-130B Public

    Forked from zai-org/GLM-130B

    GLM-130B: An Open Bilingual Pre-Trained Model

    Python