Turbo

FlashVID. [ICLR 2026 Oral] FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging

Awesome-MLLMs-Hallucination-Mitigation. Paper lists of awesome works in mitigating hallucination in Multimodal Large Language Models(MLLMs).

Awesome-MLLMs-Acceleration. Paper list of awesome works in accelerating Multimodal Large Language Models(MLLMs).

contrastive-decoding. SOTA Contrastive Decoding Strategies Implementation

MLLMs-Accelerator. State-of-the-art training-free MLLMs acceleration methods implementation

HITSZ-Digital-Image-Processing. Digital Image Processing course materials in HITSZ.

VisionZip. VisionZip Reimplementation

Awesome-MLLMs. Paper List of Awesome Multimodal Large Language Models(MLLMs).

FasterVLM. FasterVLM implementation based on LLaVA v1.5 and lmms-eval

FastV. FastV implementation based on LLaVA v1.5.

pytorch-ddpm. PyTorch implementation for Denoising Diffusion Probabilistic Model.

CSAPP-Lab. 这个仓库包含了CSAPP第三版的部分实验（Data Lab、Bomb Lab、Attack Lab、Arch Lab、Cache Lab、Shell Lab、Malloc Lab）的解决方案