Lists (4)
Starred repositories
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
nnMIL: A generalizable multiple instance learning framework for computational pathology
An open and interoperable data framework for spatial omics data
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
Democratizing AI scientists with ToolUniverse
Biomni: a general-purpose biomedical AI agent
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3, Qwen3-MoE, DeepSeek-R1, GLM4.5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, …
NuHTC: A Hybrid Task Cascade for Nuclei Instance Segmentation and Classification
[NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling
Project Imaging-X: A Survey of 1000+ Open-Access Medical Imaging Datasets for Foundation Model Development
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Integrated pipeline for multiplexed image analysis
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
Official code for ICCV2023 paper: Learning Unified Decompositional and Compositional NeRF for Editable Novel View Synthesis
Official code for ECCV2024 paper: GScream: Learning 3D Geometry and Feature Consistent Gaussian Splatting for Object Removal
Official code for paper: F3D-Gaus: Feed-forward 3D-aware Generation on ImageNet with Cycle-Aggregative Gaussian Splatting
Automate unsupervised machine learning cell type identification using both protein expressions and cell spatial neighborhood information for multiplexed in situ imaging data. No training dataset wi…
Accessible and interoperable whole slide image analysis
SlideChat: A Large Vision-Language Assistant for Whole-Slide Pathology Image Understanding (CVPR2025)
Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
Scripts for interacting with and generating data from the commercial MIBIScope