Pinned Loading

1. HiRED HiRED Public

   [AAAI 2025] HiRED strategically drops visual tokens in the image encoding stage to improve inference efficiency for High-Resolution Vision-Language Models (e.g., LLaVA-Next) under a fixed token bud…

   Python 35 4

2. PAINT PAINT Public

   [CVPR 2025 Workshop] PAINT (Paying Attention to INformed Tokens) is a plug-and-play framework that intervenes in the self-attention of the LLM and selectively boost the visual attention informed to…

   Python 8

3. Ray-Tracing- Ray-Tracing- Public

   C++ 2

4. flash-attention-optimized flash-attention-optimized Public

   Forked from tspeterkim/flash-attention-minimal

   This repository aims to optimize the forward pass of the Flash Attention implementation in CUDA. This is a part of a graduate course project titled “Emerging Topics in CS: High-Performance Code Gen…

   Cuda 1