Popular repositories Loading

1. visual-rag visual-rag Public

   Lightweight multimodal RAG pipeline for image-and-text understanding — CLIP encoding + FAISS retrieval + VLM generation

   Python 1

2. vlm-eval vlm-eval Public

   Unified evaluation harness for Vision-Language Models — VQAv2, TextVQA, COCO, MMBench, MMBench-CN

   Python 1

3. PDR_AI_v2 PDR_AI_v2 Public

   Forked from Deodat-Lawson/LaunchStack

   AI-powered document analysis platform built with Next.js, LangChain, PostgreSQL + pgvector. Upload, organize, and chat with documents. Includes predictive missing-document detection, role-based wor…

   JavaScript

4. efficient-vlp efficient-vlp Public

   Efficient vision-language pre-training toolkit: Token Merging, LoRA/QLoRA fine-tuning, Knowledge Distillation

   Python

5. loushang loushang Public

   Forked from zhnt/loushang

   AI-native coding orchestration platform: unified multi-model agent runtime with stateful sessions, tool governance, and traceable delivery.

   Python

6. AdaRubrics AdaRubrics Public

   Forked from alphadl/AdaRubrics

   AdaRubric: Adaptive Dynamic Rubric Evaluator for Agent Trajectories

   Python