Skip to content
View JSJeong-me's full-sized avatar
99 followers · 4 following
  • Hansung Univ. Seoul, Korea
  • Seoul, Korea
  • 12:32 (UTC +09:00)

Achievements

Achievement: Starstruck

Achievements

Achievement: Starstruck

Block or report JSJeong-me

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

Report abuse
JSJeong-me/README.md

Hello! ๐Ÿ‘‹ Joon Soo Jeong /PhD

LLM Agent Self-evolution, Multi-Objective Optimal Decision, ๊ทธ๋ฆฌ๊ณ  GRPO RL ๋ถ„์•ผ๋ฅผ ์—ฐ๊ตฌํ•˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.

๐Ÿ“š Recent Publications (์ตœ๊ทผ ์—ฐ๊ตฌ ์‹ค์ ) ์ฃผ์š” ์—ฐ๊ตฌ ๋ถ„์•ผ์ธ AI Agent, LLM, Scalable Reasoning, Self-Evolution ๊ด€๋ จ ๋…ผ๋ฌธ ๋ชฉ๋ก

๐Ÿ† 2025 (The Latest) ๊ฐ€์žฅ ์ตœ๊ทผ์— ๋ฐœํ‘œ๋˜์—ˆ๊ฑฐ๋‚˜ ์ง„ํ–‰ ์ค‘์ธ ์—ฐ๊ตฌ๋“ค์ž…๋‹ˆ๋‹ค.

๐Ÿš€ Scalable Reasoning via Task Decomposition and Model Routing: Achieving Near-Linear Cost in End-to-End Pipelines [PDF]

๋ถ„์•ผ: LLM, Reasoning, System Architecture

๋ฐœํ‘œ ์—ฐ๋„: 2025

โš–๏ธ MO-GRPO for Mitigating Reward Hacking in Multi-Objective LLM RL through a Variance-Equalizing Whitening Layer [PDF]

๋ถ„์•ผ: Multi-Objective Optimization (MOO), LLM RL

๋ฐœํ‘œ ์—ฐ๋„: 2025

๐Ÿค– LLM Agent์˜ ํ•ฉ๋ฆฌ์  ์˜์‚ฌ๊ฒฐ์ •์„ ์œ„ํ•œ Prompt ํ™œ์šฉ ์—ฐ๊ตฌ [PDF]

๋ถ„์•ผ: AI Agent, Prompt Engineering

๋ฐœํ‘œ ์—ฐ๋„: 2025

๐Ÿ›ก๏ธ ์•ˆ์ „ํ•˜๊ณ  ํ•ด์„ ๊ฐ€๋Šฅํ•œ AI๋ฅผ ์œ„ํ•œ GRPO(Group Relative Policy Optimization) BDI ๋ณด์ƒ ๋ชจ๋ธ [PDF]

๋ถ„์•ผ: Interpretable AI (XAI), Reinforcement Learning (RL)

๋ฐœํ‘œ ์—ฐ๋„: 2025

๐Ÿ“ฐ 2024 ์ง€๋‚œ ํ•ด ์ฃผ์š” ์—ฐ๊ตฌ ์„ฑ๊ณผ ๋ชฉ๋ก์ž…๋‹ˆ๋‹ค.

๐Ÿ“Š An Empirical Study of the Structural Understanding Capabilities of LLMs on Financial Document Tables [PDF]

๋ถ„์•ผ: LLM, Financial AI, Table Understanding

๋ฐœํ‘œ ์—ฐ๋„: 2024

๐Ÿ“ˆ LLM ๋ฉ”ํƒ€ํ”„๋กฌํŒ…์„ ํ™œ์šฉํ•œ ๊ธฐ์—… ๊ณต์‹œ๋ฌธ์„œ ๋ถ„์„์— ๊ด€ํ•œ ์—ฐ๊ตฌ [PDF]

๋ถ„์•ผ: LLM, Meta-Prompting, Finance

๋ฐœํ‘œ ์—ฐ๋„: 2024

โš™๏ธ Design and Implementation of a Condition-Based Operation (CBO) using LLM-Based Multi-Agent Systems [PDF]

๋ถ„์•ผ: Multi-Agent System, CBO, IoT

๋ฐœํ‘œ ์—ฐ๋„: 2024

๐Ÿ–ผ๏ธ Custom Hairstyle Image Generation and Similarity Analysis Using Diffuser and PEFT [PDF]

๋ถ„์•ผ: Generative AI, Diffuser, PEFT

๋ฐœํ‘œ ์—ฐ๋„: 2024

๐Ÿ”— Contact & Links

Platform Link
Email [email protected]

Pinned Loading

  1. GPT-Insights GPT-Insights Public

    2025๋…„๋„ GPT์˜ ์ตœ๊ทผ ํŠธ๋ Œ๋“œ์™€ ํ™œ์šฉ(5/8) - providing the latest insights on popular trends

    Jupyter Notebook 3 8

  2. Multimodal-Prompt-Engineering Multimodal-Prompt-Engineering Public

    Prompt-Engineering

    Jupyter Notebook 2 3

  3. Generate_AI_for_Image Generate_AI_for_Image Public

    ์ƒ์„ฑํ˜•AI๋Š” ์–ด๋–ป๊ฒŒ ์ด๋ฏธ์ง€๋ฅผ ๋งŒ๋“ค๊นŒ์š”?

    Jupyter Notebook 10 7

  4. GPT-Disclosures GPT-Disclosures Public

    GPT- Financial Accounting and Disclosures using LLM

    Jupyter Notebook 1 1

  5. GPT-Table GPT-Table Public

    GPT Table Semantic Parsing with complex & non-intuitive structure.

    Jupyter Notebook 17 2

  6. LiteLLM-OnDeive-App LiteLLM-OnDeive-App Public

    Local-LLM

    Jupyter Notebook 5