-
Tsinghua University (SIGS)
- Shenzhen, China
-
02:43
(UTC +08:00) - https://orcid.org/0000-0001-9339-2557
- https://scholar.google.com/citations?user=7HMFNfQAAAAJ
Lists (2)
Sort Name ascending (A-Z)
Stars
GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner in WWW'23
[CVPR 2024 Highlight] Logit Standardization in Knowledge Distillation
Reference implementation of Megalodon 7B model
Clinical Histopathology Imaging Evaluation Foundation Model
Hiera: A fast, powerful, and simple hierarchical vision transformer.
The official implementation for ICLR23 spotlight paper "DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion"
Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models
A curated collection of research papers exploring the utilization of LLMs for graph-related tasks.
Fast and memory-efficient exact attention
Implementation of SETR model, Original paper: Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers.
Using Somatic genome alterations (SGAs) and cancer type to predict drug response with the model named "ResGitDR"
QLoRA: Efficient Finetuning of Quantized LLMs
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
PyTorch code and models for the DINOv2 self-supervised learning method.
[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
Leveraging Pre-trained Models for FF-to-FFPE Histopathological Image Translation
HEST: Bringing Spatial Transcriptomics and Histopathology together
Low rank adaptation for Vision Transformer
Prov-GigaPath: A whole-slide foundation model for digital pathology from real-world data
1.5−3.0× lossless training or pre-training speedup. An off-the-shelf, easy-to-implement algorithm for the efficient training of foundation visual backbones.
[MICCAI 2024] Official Repo of "HistGen: Histopathology Report Generation via Local-Global Feature Encoding and Cross-modal Context Interaction"
Official Inplementation of 《WsiCaption: Multiple Instance Generation of Pathology Reports for Gigapixel Whole Slide Images》(MICCAI 2024 oral)
xmuyulab / CAMELYON
Forked from wilmerwang/SLFCDThe solution to cameyon16 and camelyon17 challenge and also to your own WSI data project.