Skip to content
View Kshitij-Ambilduke's full-sized avatar
🤖
Aspiring to be inspiring
🤖
Aspiring to be inspiring
27 followers · 23 following
  • IvLabs
  • VNIT, Nagpur

Achievements

Achievement: QuickdrawAchievement: Pull Shark

Achievements

Achievement: QuickdrawAchievement: Pull Shark

Organizations

@IvLabs

Block or report Kshitij-Ambilduke

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.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, 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
Kshitij-Ambilduke/README.md

Hi there 👋, I am Kshitij Ambilduke

I am a Machine learning enthusiast stuck somewhere between Vision, Language and Sound.

I try to make Machine Learning models which sometimes caption images of dogs as cat and speaks of it as a rat.

I am currently pursuing my master's in computer science (Artificial Intelligence track) at Université Paris-Saclay. Previously, I worked as a trainee researcher at the Instituto de Telecomunicações, Lisbon.

  • 😄 I graduated from VNIT, India in 2023, I completed by B.Tech. in Electronics and Communication Engineering from there.
  • 🔭 I’m currently working on Language Modelling and Multimodal Learning.
  • 🌱 I have been studying Deep Learning models and its application to Visual, Lingual and speech domains.
  • 🤝 I’m up for collaborating over Deep Learning, Natural Language Processing, Multimodal Learning projects.
  • 💬 Ping me if you want to know anything about me on kshitij.a.vnit@gmail.com

Pinned Loading

  1. IvLabs/Natural-Language-Processing IvLabs/Natural-Language-Processing Public

    Contains various architectures and novel paper implementations for Natural Language Processing tasks like Sequence Modelling and Neural Machine Translation.

    Jupyter Notebook 49 9

  2. Memes-vs-Notes Memes-vs-Notes Public

    Jupyter Notebook 7

  3. Hierarchical Question-Image Co-Atten... Hierarchical Question-Image Co-Attention for Visual Question Answering.md
    1 
    # Hierarchical Question-Image Co-Attention for Visual Question Answering
    2 
    > Sauce : https://arxiv.org/abs/1606.00061
    3
    4 
    The paper presents a novel Co-Attention mechanism for VQA that jointly reasons about image and question attentions. (SOTA - 2017)
    5 
    
              
    
          
    
    
    
  
    

    4. 

      
  4. 
  
    
    
    
      
    
        
    
            
          Visual-Transformers  Visual-Transformers          Public
        
    
      
    


      
    
        Re-implementation of Visual Transformers: Token-based Image Representation and Processing for Computer Vision for image classification for CIFAR-10 and MNIST datasets
      
    

      
    
          
  
  Jupyter Notebook


          
            
    

            6
          
          
            
    

            2
          
      
    
    
    
  
    

    5. 

      
  5. 
  
    
    
    
      
    
        
    
            
          MedVQA  MedVQA          Public
        
    
      
    


      
    
        medical visual question answering 
      
    

      
    
          
  
  Python


          
            
    

            9
          
          
            
    

            1
          
      
    
    
    
  
    

    6. 

      
  6. 
  
    
    
    
      
    
        
    
            
          VQA  VQA          Public
        
    
      
    


      
    
        
      
    

      
    
          
  
  Jupyter Notebook


          
            
    

            3
          
      
    
    
    
  
    

    7.