Focusing
PhD student in Computer Vision
-
The University of Hong Kong
- Hong Kong
- https://scholar.google.com/citations?hl=zh-CN&user=QC7nNe0AAAAJ
Highlights
- Pro
Starred repositories
Class materials, homeworks and videos for probation preparation.
19
Updated Feb 3, 2026
[TKDE'25] The official GitHub page for the survey paper "A Survey on Mixture of Experts in Large Language Models".
Ming - facilitating advanced multimodal understanding and generation capabilities built upon the Ling LLM.
[CVPR 2026] Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens
Awesome Reasoning LLM Tutorial/Survey/Guide
From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1
A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.
This is a repository for organizing papers, codes, and other resources related to Latent Reasoning.
This repository contains a regularly updated paper list for LLMs-reasoning-in-latent-space.
PyTorch implementation of JiT https://arxiv.org/abs/2511.13720
[NeurIPS 2025 Oral]Infinity: Unified Spacetime AutoRegressive Modeling for Visual Generation
Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"
Official implementation of "OmniX: From Unified Panoramic Generation and Perception to Graphics-Ready 3D Scenes".
Math-VR Benchmark & CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images
This is the official repository for the paper "FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark"
[NeurIPS 2025] Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations
[ICLR 2026] PixNerd: Pixel Neural Field Diffusion
Pixel-Level Reasoning Model trained with RL [NeuIPS25]
[ICLR 2025] VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation
Famous Vision Language Models and Their Architectures
Awesome Unified Multimodal Models
Nuo Ya Pan Gu Da Mo Xing Yan Fa Bei Hou De Zhen Zheng De Xin Suan Yu Hei An De Gu Shi .
Empowering Unified MLLM with Multi-granular Visual Generation
[ICCV 2025] Official implementation of the paper "DreamCube: 3D Panorama Generation via Multi-plane Synchronization".
A Collection of Papers on Diffusion Language Models