Revliter

LLaVA-NeXT

LLaVA

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

NaViT

My implementation of "Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution"

MyGO

[Paper][Preprint 2024] MyGO: Discrete Modality Information as Fine-Grained Tokens for Multi-modal Knowledge Graph Completion

NJUThesis

南京大学学位论文模板

whisper

Robust Speech Recognition via Large-Scale Weak Supervision

MoViNet-pytorch

MoViNets PyTorch implementation: Mobile Video Networks for Efficient Video Recognition;

DCI

Densely Captioned Images (DCI) dataset repository.

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

Awesome-Dataset-Distillation

A curated list of awesome papers on dataset distillation and related applications.

transformer-debugger

VideoMamba

[ECCV2024] VideoMamba: State Space Model for Efficient Video Understanding

math

The MATH Dataset (NeurIPS 2021)

test

Measuring Massive Multitask Language Understanding | ICLR 2021

OpenDiT

OpenDiT: An Easy, Fast and Memory-Efficient System for DiT Training and Inference

maws

Code and models for the paper "The effectiveness of MAE pre-pretraining for billion-scale pretraining" https://arxiv.org/abs/2303.13496

VideoMAE

[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

Vim

[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

CLIP_benchmark

CLIP-like model evaluation

bagel

A bagel, with everything.

lm-evaluation-harness

A framework for few-shot evaluation of language models.

flash-attention

Fast and memory-efficient exact attention

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

unmasked_teacher

[ICCV2023 Oral] Unmasked Teacher: Towards Training-Efficient Video Foundation Models

moco

PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722

dino

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

omnivore

Omnivore: A Single Model for Many Visual Modalities

Awesome-Multimodal-Large-Language-Models

:sparkles::sparkles:Latest Advances on Multimodal Large Language Models

Awesome-Knowledge-Distillation

Awesome Knowledge-Distillation. 分类整理的知识蒸馏paper(2014-2021)。

awesome-knowledge-distillation

Awesome Knowledge Distillation