PinnedLoading

1. HiREDHiREDPublic

   [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 26 4

2. PAINTPAINTPublic

   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 tokens to mitigate hall…

   Python 6

3. Ray-Tracing-Ray-Tracing-Public

   C++ 2

4. LLaVALLaVAPublic

   Forked fromhaotian-liu/LLaVA

   [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

   Python

5. Lines-Of-ActionLines-Of-ActionPublic

   Java 1

6. Rasterization-based-computer-graphics-PipelineRasterization-based-computer-graphics-PipelinePublic

   4 stages of the pipeline. 1. Stage 1: modeling transformation 2. Stage 2: view transformation 3. Stage 3: projection transformation 4. Stage 4: clipping & scan conversion using Z-buffer algorithm

   C++