Skip to content
View bbsngg's full-sized avatar
🎯
Focusing
🎯
Focusing
33 followers · 37 following

Achievements

Achievement: Pair Extraordinairex3Achievement: Starstruckx3Achievement: Pull Sharkx2Achievement: YOLOAchievement: Arctic Code Vault Contributor

Achievements

Achievement: Pair Extraordinairex3Achievement: Starstruckx3Achievement: Pull Sharkx2Achievement: YOLOAchievement: Arctic Code Vault Contributor

Block or report bbsngg

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
bbsngg/readme.md

Dingjie Song

AI researcher building practical intelligent systems.

I work at the intersection of research and engineering: turning ideas into usable ML workflows, prototypes, and products.

Current Focus

  • Building toward AI Scientist style systems and research workflows
  • Applying machine learning to real problems with strong engineering discipline
  • Exploring tools that make experimentation, reasoning, and iteration faster

Selected Stack

Python PyTorch TensorFlow scikit-learn Pandas OpenCV

JavaScript React Vue Node.js

Java Rust C Spring

MongoDB MySQL Oracle

Links

GitHub Snapshot

GitHub stats for bbsngg Top languages for bbsngg

Pinned Loading

  1. OpenLAIR/dr-claw OpenLAIR/dr-claw Public

    A Super AI Lab with massive AI Doctors as Assistants. Best IDE for Research via AI Power.

    JavaScript 1.2k 141

  2. OpenLAIR/OpenSkill OpenLAIR/OpenSkill Public

    Open-World Self-Evolution for LLM Agents — agents that build both their skills and their own verification signals from scratch, with no target-task supervision. (Code coming soon.)

    PDDL 99 4

  3. OpenLAIR/lev OpenLAIR/lev Public

    Lev: Thinking Fast and Deep with Looped Decision Models. One checkpoint, multiple depths: System 1.5 decision models that think in loops, not tokens.

    Python 27 1

  4. MileBench/MileBench MileBench/MileBench Public

    This repo contains evaluation code for the paper "MileBench: Benchmarking MLLMs in Long Context"

    Python 38 2

  5. FreedomIntelligence/TRIM FreedomIntelligence/TRIM Public

    We introduce new approach, Token Reduction using CLIP Metric (TRIM), aimed at improving the efficiency of MLLMs without sacrificing their performance.

    Python 23 1

  6. FreedomIntelligence/CMB FreedomIntelligence/CMB Public

    CMB, A Comprehensive Medical Benchmark in Chinese

    Python 255 25