Kaiyang

@kaiyangzhou

Assistant Professor at HKBU working on machine learning & computer vision. Self-appointed portfolio manager.

kaiyangzhou.github.io

Joined March 2015

Replies Reposts Media

Kaiyang
@kaiyangzhou
Mar 25
keeping up with the trend🔥🔥🔥
The AI Talks
@TheAITalksOrg
Mar 24
🎙️The AI Talks 3D World Model for Robotics - by Wenlong Huang @wenlong_huang Can we teach robots to imagine the future before they act? From building a 3D intuition for physics with PointWorld to zero-shot synthesis of real-world manipulation skills, let's dive in. Join us👇
1
Kaiyang
@kaiyangzhou
Mar 12
This is a timely work that addresses the memory issue in FMs using parameter generation
Tencent Hy
@TencentHunyuan
Mar 5
One static model does not fit all😭 We just dropped our latest work: Functional Neural Memory. Instead of static models, we generate custom "parameters" for every single input. ✅Prompt your model anytime ✅Instant personalization ✅Better instruction following ✅Flexible &
00:00
Kaiyang
@kaiyangzhou
Mar 1
🚀 Introducing Streamo: Real-time streaming video LLM mastering narration, event grounding & time-sensitive QA! Powered by Streamo-Instruct-465K dataset. Bridges offline video models to interactive assistants. #AI #ComputerVision #VideoLLM #CVPR2026 jiaerxia.github.io/Streamo/
Xia Jiaer
@JiaerXia
Mar 1
Build a real-time AI assistant! 🎥 Streamo (to appear in #CVPR2026) enables turning any offline LLM into a live streaming video model. Key features: 💫 Real-time interaction ✨ Diverse instructions 🌟 Multi-task capable Code:github.com/maifoundations… Paper:arxiv.org/pdf/2512.21334
00:00
Kaiyang
@kaiyangzhou
Jan 30
Often encounter the out-of-memory problem when finetuning foundation models (LLM, VLM, ...)? Try QZO (to appear in #ICLR2026), a memory efficient training method enabling zeroth-order optimization on quantized models paper: arxiv.org/pdf/2505.13430 code: github.com/maifoundations…
1
Kaiyang
@kaiyangzhou
Jan 14
just went through the work very nice paper highly recommend
Brian Li
@Brian_Bo_Li
Jan 13
Just read an excellent survey paper on AI agents. Measuring Agents in Production 📄 Paper: arxiv.org/pdf/2512.04123 🎬 Explained Video (Chinese): bilibili.com/video/BV1rkBNB… It gave me an epiphany about the real status of agents in production and prompted me to reflect on what
1