Pinned Loading

1. FiCoCo FiCoCo Public

   [AAAI 26'] This is the official pytorch implementation for paper: Filter, Correlate, Compress: Training-Free Token Reduction for MLLM Acceleration

   Python 45 1

2. MAPGD MAPGD Public

   Official implementation of "MAPGD: Multi-Agent Prompt Gradient Descent for Collaborative Prompt Optimization"

   Python 17

3. InnovatorLM/Innovator-VL InnovatorLM/Innovator-VL Public

   Fully Open-source Multimodal Language Models for Science Discovery

   Python 153 10

4. STaR-KV STaR-KV Public

   Official implementation of STaR-KV: training-free spatio-temporal KV cache compression for efficient GUI vision-language models.

   Python 15