Stars
[ICCV 2023] Consistent Image Synthesis and Editing
GrapHist: Graph Self-Supervised Learning for Histopathology
The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.
The hub for EleutherAI's work on interpretability and learning dynamics
Study analyzing how weight tying affects the relationship between input (embedding) and output (unembedding) matrices in language models.
Implementing C-RADIOv4 as a Remote Source Zoo Model for FiftyOne
[CVPR 2026] - IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment
Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders [Technical Report]
Code repo for "EvoTok: A Unified Image Tokenizer via Residual Latent Evolution for Visual Understanding and Generation"
[Nature Communications 2026] A universal foundation model for grounded biomedical image interpretation
UrFound: Towards Universal Retinal Foundation Models via Knowledge-Guided Masked Modeling
[MICCAI 2025 Early Accept] PRETI: Patient-Aware Retinal Foundation Model via Metadata-Guided Representation Learning
Official codebase for RetFiner: A Vision-Language Refinement Scheme for Retinal Foundation Models
[IEEE TPAMI 2025] This repository is the official implementation of the paper "VisionUnite: A Vision-Language Foundation Model for Ophthalmology Enhanced with Clinical Knowledge"
Versatile and Open Large Models for Ophthalmology
A topic-centric list of HQ open datasets.
This is a user guide for the MiniCPM and MiniCPM-V series of small language models (SLMs) developed by ModelBest. “面壁小钢炮” focuses on achieving exceptional performance on the edge.
Identification and Validation Robust Prognostic Biomarkers and Signatures in Solid Tumors
Comparing text compression performance of LLMs with traditional compression approaches.
Frontiers in Intelligent Colonoscopy [ColonSurvey | ColonINST | ColonGPT]
AniMer: Animal Pose and Shape Estimation Using Family Aware Transformer (CVPR2025)
EfficientSAM3 compresses SAM3 into lightweight, edge-friendly models via progressive knowledge distillation for fast promptable concept segmentation and tracking.
Official code "Taming SAM3 in the Wild: A Concept Bank for Open-Vocabulary Segmentation"