A novel medical large language model family with 13/70B parameters, which have SOTA performances on various medical tasks

The first Chinese Multimodal Medical Knowledge Graph

A flexible framework powered by ComfyUI for generating personalized Nobel Prize images.

First Multimodal Traditional Chinese Medicine Dataset

[NIPS'24] Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection

[NeurIPS2024] An official pytorch implement of the paper "ReFIR: Grounding Large Restoration Models with Retrieval Augmentation".

[Paper List] Papers integrating knowledge graphs (KGs) and large language models (LLMs)

Offical code of "QKFormer: Hierarchical Spiking Transformer using Q-K Attention" (NeurIPS 2024，Spotlight 3%)

Easily download and evaluate pre-trained Visual Place Recognition methods. Code built for the ICCV 2023 paper "EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition"

[NeurIPS'24] MemVLT: Vision-Language Tracking with Adaptive Memory-based Prompts

Heterogeneous Pre-trained Transformer (HPT) as Scalable Policy Learner.

Resources about Sign Language Processing (e.g., Sign Language Recognition / Translation / Production)

[Nature Communications] The official codes for "Towards Building Multilingual Language Model for Medicine"

Source code for EvMAPPER

[CVPR'23] Code for "SCOTCH and SODA: A Transformer Video Shadow Detection Framework".

This is the official code for "Enhancing Perception of Key Changes in Remote Sensing Image Change Captioning"

This is an Online Test-time Adaptation (OTTA) benckmark conducted on ViT backbones.

g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains

Physics-informed neural networks package

Kolmogorov Arnold Networks

[ACMMM 2024 (Oral)] MICM: Rethinking Unsupervised Pretraining for Enhanced Few-shot Learning