Skip to content
View romsto's full-sized avatar
22 followers · 18 following

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 userโ€™s behavior. Learn more about reporting abuse.

Report abuse
romsto/README.md

Hello, I am Romain ๐Ÿ‘‹

๐Ÿ’ก Looking for role as a Research Engineer, Software Engineer, or Research Scientist in Large Language Models. Available immediately.

๐ŸŽ“ Graduated with a dual degree:
M.S. in Computer Science and Engineering @ Seoul National University (์„œ์šธ๋Œ€ํ•™๊ต).
M.Eng. in Engineering and AI @ IMT Mines Alรจs.

๐Ÿ”ฌ Research Interests:
I aim to incorporate human behaviors into LLMs to improve their performance and efficiency.
(Adaptive Computation in Transformers; LLM Post-Training; LLM Decoding & Optimization)

๐Ÿ›๏ธ Previously at: Language and Data Intelligence Lab (ldi.snu.ac.kr) under Prof. Hwang (ํ™ฉ ๊ต์ˆ˜๋‹˜).

๐ŸŒ Based in France ๐Ÿ‡ซ๐Ÿ‡ท

Website Linkedin: romain-storaรฏ Stars

$ cat romain.py

from profiles import ResearchEngineer


class Romain(ResearchEngineer):
    def __init__(self):
        self.name = "Romain"
        self.focus = ["Adaptive Computation", "LLM Inference"]
        self.education = [
            "M.S. @ Seoul National University ๐Ÿ‡ฐ๐Ÿ‡ท",
            "M.Eng. @ IMT Mines Alรจs ๐Ÿ‡ซ๐Ÿ‡ท"
        ]
        self.attribute = Curious(level=math.inf)
        self.location = "France"  # South Korea
 
    def mode(self):
        return "๐Ÿ”ฌ Research | ๐Ÿ› ๏ธ Engineering"  # Swiss Army knife mode activated

    def contact(self):
        return "[email protected]"

Pinned Loading

  1. HARP HARP Public

    Official Implementation of HARP: Hesitation-Aware Reframing in Transformer Inference Pass (Romain Storaรฏ 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 45 8

  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 3

  4. RushHour RushHour Public

    Play the famous boardgame and Solve the puzzle automatically

    Java 1