Skip to content
View BinWang28's full-sized avatar
🎯
Focusing
🎯
Focusing
253 followers · 189 following

Achievements

Achievement: Pair Extraordinairex4Achievement: Pull Sharkx3Achievement: YOLOAchievement: QuickdrawAchievement: Starstruckx3Achievement: Arctic Code Vault Contributor

Achievements

Achievement: Pair Extraordinairex4Achievement: Pull Sharkx3Achievement: YOLOAchievement: QuickdrawAchievement: Starstruckx3Achievement: Arctic Code Vault Contributor

Organizations

@USC-MCL @emnlp-2023 @SeaEval @NLGPerson @AudioLLMs @MiroMindAI

Block or report BinWang28

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 is supported. 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
BinWang28/README.md

Hi there, I'm Bin Wang 👋

AI Tech Builder · LLM Generalist · Data & Models

🧭 About Me

  • 🏢 Building AI at MiroMind, Singapore
  • 🔬 Working across the LLM stack — pre/post-training, agents, audio, evaluation — currently focused on large-scale data processing & infra (Ray, distributed pipelines, scale-up environments)
  • 🌏 Active in the open-source AI community — maintainer / contributor across @MiroMindAI, @AudioLLMs, @SeaEval
  • ✍️ Personal site & writing: binwang.xyz

🚀 Featured Projects

Project Description Stars
🧠 MiroThinker SOTA deep research agent — 74.0 / 75.3 on BrowseComp / BrowseComp-Zh ⭐ 8k+
🌊 MiroFlow Top-1 on 5+ agent benchmarks · Web UI · multi-model ⭐ 3k+
🎧 AudioBench Universal benchmark for Audio LLMs ⭐ 300+
📚 audio-ai-hub Curated hub for Audio LLM research ⭐ 900+
📐 SBERT-WK IEEE/ACM TASLP 2020 — sentence embedding via BERT dissection ⭐ 180+

🛠️ Tech I Work With

💬 Happy to chat tech — drop me a line if something here interests you.
⚠️ Not open to research / paper collaborations — especially remote ones. Please don't reach out for co-authorship unless you genuinely believe I can make a unique contribution to the research.

Pinned Loading

  1. MiroMindAI/MiroThinker MiroMindAI/MiroThinker Public

    MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.

    Python 8.2k 637

  2. MiroMindAI/MiroFlow MiroMindAI/MiroFlow Public

    🏆 Top-1 on 5+ benchmarks | Web UI | Supports MiroThinker, Claude, Kimi, OpenAI

    Python 3k 312

  3. audio-ai-hub audio-ai-hub Public

    The hub for audio AI research: papers, open models, benchmarks & datasets across audio LLMs, speech recognition, TTS, music & audio generation.

    Python 922 48

  4. AudioLLMs/AudioBench AudioLLMs/AudioBench Public

    AudioBench: A Universal Benchmark for Audio Large Language Models

    Python 310 15