Skip to content
View romsto's full-sized avatar

Organizations

@ldilab

Block or report romsto

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
romsto/README.md

Hello, I am Romain 👋

🎓 Currently pursuing a M.S. in Computer Science and Engineering at Seoul National University (서울대학교)

🔬 Research Interests: My goal is to improve the efficiency and performance of language models without retraining or fine-tuning.

  • LLM Decoding
  • LLM Optimization
  • Information Retrieval

🏛️ Lab: Language and Data Intelligence Laboratory (ldi.snu.ac.kr), under the supervision of Prof. Hwang (황 교수님).

Website Linkedin: romain-storaï Stars

class Romain extends Student {
    
    final String username;
    String location;
    String[] skills;
    
    Romain() {
        username = "romsto";
        location = "South Korea"; // "France"
        skills = {"Large Language Models", "Deep Learning", "Software Engineering"};
    }
    
    Education[] getEducation() {
        Education[] myEducation = new Education[2];

        // Currently attending
        myEducation[1] = new EducationBuilder().degree(Degree.MASTER_OF_SCIENCE)
                                                .university("Seoul National University")
                                                .subjects("AI", "Natural Language Processing", "LLM", "Transformers")
                                                .attending();

        myEducation[0] = new EducationBuilder().degree(Degree.MASTER_OF_ENGINEERING)
                                                .university("IMT Mines Alès")
                                                .subjects("Computer Science", "AI", "General Engineering")
                                                .finished();

        return myEducation;
    }
    
    String[] getGoals() {
        return {"Feed my curiosity", "Contribute to humanity", "Accelerate & Improve LLMs"};
    }
    
    String getContact() {
        return "romsto@snu.ac.kr";
    }
}

Pinned Loading

  1. HARP HARP Public

    Official Implementation of HARP: Hesitation-Aware Reframing in Transformer Inference Pass (Romain Storaï and Seung-won Hwang, 2024)

    Python 4 1

  2. Speculative-Decoding Speculative-Decoding Public

    Implementation of the paper Fast Inference from Transformers via Speculative Decoding, Leviathan et al. 2023.

    Python 31 1

  3. Inappropriate-Language-Classifier Inappropriate-Language-Classifier Public

    Online video games need a better system to detect inappropriate language in chat, and using machine learning models could help create a safer and more enjoyable environment for all players.

    Jupyter Notebook 2

  4. RushHour RushHour Public

    Play the famous boardgame and Solve the puzzle automatically

    Java 1