Skip to content
View abhishekjoshi007's full-sized avatar
TroubleShooting
TroubleShooting

Block or report abhishekjoshi007

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
abhishekjoshi007/README.md

Hey there 👋 I'm Abhishek Joshi

🎓 PhD-track AI Researcher  |  ⚡ Edge-ML Builder  |  🌍 Open-source Advocate
Texas A&M University–Corpus Christi • iCORE Lab

LinkedIn Email Google Scholar view count


🔎 About Me

  • 🧠 Research focus: GNNs, diffusion & transformer models, trustworthy LLMs
  • 🔌 Current work: AI-driven geospatial microgrids & EV-charging optimization
  • 📝 Publications: IEEE CAI ’25 • IEEE BIG DATA ’24 • LLM calibration study (rev.)
  • 🥇 Wins: National Smart India Hackathon champion (EV range prototype)
  • 🎤 Leadership: Session Chair – IEEE CAI 2025 (Graph Learning & Visualization) and Peer Reviewer DMI 2025 Assessed three AI papers on LLM & RAG.

🛠️ Tech Toolkit

Python JavaScript TypeScript C C++ Java SQL

PyTorch TensorFlow Hugging Face Stable Diffusion DGL

Docker Kubernetes AWS GCP dbt Airflow Weights & Biases


🌟 Highlighted Projects

  • Business Build AI — No-code branding generator blending Stable Diffusion & OpenAI; slashes content-creation time by 50 %.
  • Content Right — Text-to-video pipeline (TensorFlow + React) boosting engagement by 40 %.
  • ConvTTrans + ConvLSTM — Edge-ready hybrid vision model for video anomaly detection on Jetson devices.
  • Microgrid Forecaster — Graph-based tool that shaved 7 % off evening peak load on campus.
  • HiFi-GAN Mobile Vocoder — 3 kbps speech codec running <30 ms on iPhone (CoreML + XNNPACK).

Detailed write-ups & code in pinned repos.


📚 Recent Publications

  • IEEE CAI 2025: Real-Time Adaptive Multi-Modal Stock Prediction with Temporal Graph Attention
  • IEEE BIG DATA 2024: Multi-Modal Transformer for Sturdy Stock Return Forecasting
  • (Under Review): Calibration Limits of LLMs in Implicit Hate-Speech Detection

🎤 Community & Leadership

💬 Session Chair, IEEE CAI 2025 | 🌐 Workshop Lead, IEEE PES RES Robotics 2024 | 🚀 Mentor, IEEE YP Hackathon (Smart Microgrid Analytics)


📈 Stats


Transforming raw data into resilient, human-centered energy & AI solutions.Abhishek

Pinned Loading

  1. Real-Time-Adaptive-Multi-Modal-Stock-Prediction Real-Time-Adaptive-Multi-Modal-Stock-Prediction Public

    Real-Time Adaptive Multi-Modal Stock Prediction with Temporal Graph Attention and Dynamic Interaction Networks

    Python 4 1

  2. A-Multi-Modal-Transformer-Architecture-Combining-Sentiment-Dynamics-Temporal-Market-Data A-Multi-Modal-Transformer-Architecture-Combining-Sentiment-Dynamics-Temporal-Market-Data Public

    Our approach uniquely fuses sentiment dynamics from social media and news sources with temporal market data and macroeconomic indicators to construct dynamic graph representations of interfirm rela…

    Python 2 1

  3. Business_Build_AI Business_Build_AI Public

    Business-Build-AI is an automated website builder that leverages the power of AI to generate content and images for your website. The application uses OpenAI API for content creation and Stable Dif…

    TypeScript 1

  4. Real-Time-Face-Detection-Using-API Real-Time-Face-Detection-Using-API Public

    JavaScript

  5. XDLANG-Compiler-Introduction-to-LLVM XDLANG-Compiler-Introduction-to-LLVM Public

    Python