Repositories
24wanwu
PublicChina Unicom's Yuanjing Wanwu Agent Platform is an enterprise-grade, multi-tenant AI agent development platform. It helps users build applications such as intelligent agents, workflows, and rag, and also supports model management. The platform features a developer-friendly license, and we welcome all developers to build upon the platform.
MeanCache
Public[ICLR 2026] MeanCache: From Instantaneous to Average Velocity for Accelerating Flow Matching Inference
LeMiCa
Public[NeurIPS 2025 Spotlight] LeMiCa: Lexicographic Minimax Path Caching for Efficient Diffusion-Based Video Generation
wanwu-workflow
Public本项目是基于coze-studio项目进行的二次开发,遵循其Apache 2.0 协议许可证。主要修改并使用其工作流部分的代码,作为联通元景万悟智能体平台的工作流模块。
CoTj
PublicCoTj (Chain-of-Trajectories) upgrades diffusion models from fixed System-1 denoising schedules to System-2 style, condition-adaptive trajectory planning via graph optimization.
UnicomBenchmark
PublicUnicomAI Large Model Benchmark
HiMo-CLIP
Public[AAAI 2026 Oral] HiMo-CLIP: Modeling Semantic Hierarchy and Monotonicity in Vision-Language Alignment
DocParserServer
PublicConvert pdf documents to markdown
UniT2IXL
PublicTrajXfer
PublicA lightweight, few-shot acceleration framework for flow matching models based on trajectory straightening and visual fidelity transfer.
Unichat-llama3-Chinese
PublicPSTF-AttControl
PublicPSTF-AttControl: Per-subject-tuning-free personalized image generation with controllable face attributes (Image and Vision Computing)
UnicomAI.github.io
PublicShortDF
PublicOptimizing for the Shortest Path in Denoising Diffusion Model (CVPR2025)
DeepSeek-R1-Safe
PublicA collection of DeepSeek-R1-Distill models finetuned for model safety.
Unichat-32B-c1
PublicDeepSeek-Eval
Publicwanwu-mcp
PublicUnicomAI
PublicConfig files for my GitHub profile.
DeepSeek-R1-Distill-Safe
PublicA collection of DeepSeek-R1-Distill models finetuned for model safety.
Unichat-DeepSeek-R1-distill-32B
PublicLKHAT
PublicEmbodiedGPT_Pytorch
Public Forkpiculet
PublicPiculet: Specialized Model-Guided Hallucination Alleviation for MultiModal Large Language Models