wwyi1828
Follow
Stars
[ICLR 2026] EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward Modeling
EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing [ICLR 2026]
[CVPR 2025] Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment
This repository open-sources CreatiPoster, an AI-driven graphic design generation system for multi-layer and editable compositions with strong visual appeal.
The official implementation of "Diffusion Probe: Generated Image Result Prediction Using CNN Probes", accepted as a poster at CVPR 2026.
Official implementation of ImageCritic (CVPR 2026)
[CVPR2026 Findings] VHS: Verifier on Hidden States, an efficient inference-time scaling verification framework for DiT-based image generation.
[CVPR 2026] Garments2Look: A Multi-Reference Dataset for High-Fidelity Outfit-Level Virtual Try-On with Clothing and Accessories
Qwen-Image-Layered: Layered Decomposition for Inherent Editablity
UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generation
[CVPR 2026F] Learning Spatial-Preserving Hierarchical Representations for Digital Pathology
Personality detection on multiparty dialogue
[ICLR 2025] CatVTON is a simple and efficient virtual try-on diffusion model with 1) Lightweight Network (899.06M parameters totally), 2) Parameter-Efficient Training (49.57M parameters trainable) …
Official inference repo for FLUX.1 models
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
Reference PyTorch implementation and models for DINOv3
The simplest, fastest repository for training/finetuning medium-sized GPTs.
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
[ICCV 2023] Improving Representation Learning for Histopathologic Images with Cluster Constraints
From Pattern Recognizers to Personalized Companions: A Survey of Large Language Models in Mental Health (TAFFC)
将冰冷的离别化为温暖的 Skill，欢迎加入数字生命1.0！Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0. 🫶
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.