zhixiangwei's picture

8 8 24

zhixiangwei PRO

zhixiangwei

·

AI & ML interests

None yet

Recent Activity

new activity 3 days ago

tencent/Youtu-VL-4B-Instruct:[Urgent Suggestion] Complete Deployment Guide: SDPA Patch (2x speed), 4-bit Fix for 8GB GPUs & Visual Examples

new activity 8 days ago

tencent/Youtu-VL-4B-Instruct:Add link to Demo for VL and CV tasks to README

new activity 8 days ago

tencent/Youtu-VL-4B-Instruct:Fixing line break & Critical feedback on missing features (OD/Segmentation)

View all activity

Organizations

None yet

authored 4 papers 15 days ago

Disentangle then Parse:Night-time Semantic Segmentation with Illumination Disentanglement

Paper • 2307.09362 • Published Jul 18, 2023 • 1

Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation

Paper • 2312.04265 • Published Dec 7, 2023 • 2

HQ-CLIP: Leveraging Large Vision-Language Models to Create High-Quality Image-Text Datasets and CLIP Models

Paper • 2507.22431 • Published Jul 30, 2025 • 1

Youtu-VL: Unleashing Visual Potential via Unified Vision-Language Supervision

Paper • 2601.19798 • Published 17 days ago • 42