Skip to content
View IrohXu's full-sized avatar
❄️
Working from North
❄️
Working from North
60 followers · 26 following

Achievements

Achievement: Pull Sharkx2Achievement: YOLOAchievement: Pair ExtraordinaireAchievement: Starstruckx2Achievement: Public SponsorAchievement: Arctic Code Vault Contributor

Achievements

Achievement: Pull Sharkx2Achievement: YOLOAchievement: Pair ExtraordinaireAchievement: Starstruckx2Achievement: Public SponsorAchievement: Arctic Code Vault Contributor

Block or report IrohXu

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
IrohXu/README.md

Hi there 👋

I have moved from US to Canada for full-time roles.

I will come to COLM 2025 (Montreal, Canada) from October 7-10, 2025. Feel free to send me an email for a coffee chat there!

📫 Research Update

Our paper What is the Visual Cognition Gap between Humans and Multimodal LLMs? has been accepted by COLM 2025.

Our paper SocialGesture: Delving into Multi-person Gesture Understanding has been accepted by CVPR 2025.

I am leading the organization of the ICLR 2025 Workshop on AI for Children. As a former patient with a rare pediatric disease, I am deeply committed to leveraging AI to improve healthcare outcomes for children facing medical challenges. Through my workshop, I hope to found a team to foster interdisciplinary discussions and drive impactful research in AI-driven pediatric care.

⚡️ A quick introduction

Researcher for Embodied AI, AI for Low-resource Setting, AI for Social Good

🤝🏻 Connect, Follow, Subscribe

🤔 Twitter 🤔 LinkedIn
🤔 Email: xucao [at] pediamed [dot] ai

Pinned Loading

  1. huggingface/diffusers huggingface/diffusers Public

    🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

    Python 30.6k 6.3k

  2. Awesome-Multimodal-LLM-Autonomous-Driving Awesome-Multimodal-LLM-Autonomous-Driving Public

    [WACV 2024 Survey Paper] Multimodal Large Language Models for Autonomous Driving

    293 13

  3. lanenet-lane-detection-pytorch lanenet-lane-detection-pytorch Public

    Unofficial implemention of lanenet model for real time lane detection Pytorch Version

    Python 166 40

  4. PediaMedAI/PIE PediaMedAI/PIE Public

    PIE: Simulating Disease Progression via Progressive Image Editing

    Python 28 1

  5. LLVM-AD/MAPLM LLVM-AD/MAPLM Public

    [CVPR 2024] MAPLM: A Large-Scale Vision-Language Dataset for Map and Traffic Scene Understanding

    Python 149 3

  6. PediaMedAI/ViTASD PediaMedAI/ViTASD Public

    [ICASSP 2023] Official Implementation of ViTASD: Robust Vision Transformer Baselines for Autism Spectrum Disorder Facial Diagnosis

    Python 27 6