Liushiyu-0709
Follow
Stars
Ready-to-use code and tutorial notebooks to boost your way into few-shot learning for image classification.
Code for our IJCV 2023 paper "CLIP-guided Prototype Modulating for Few-shot Action Recognition".
Watch, read and lookup: learning to spot signs from multiple supervisors, ACCV 2020 (Best Application Paper)
The official implementation of the paper "SCOPE: Sign Language Contextual Processing with Embedding from LLMs".
Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audi…
A curated list of awesome prompt/adapter learning methods for vision-language models like CLIP.
This is the official code repository for the paper 'Improving Gloss-free Sign Language Translation by Reducing Representation Density'.
OpenAI CLIP text encoders for multiple languages!
Large-Vocabulary Continuous Sign Language Recognition, 2024
🔥🔥🔥Latest Papers, Codes and Datasets on Vid-LLMs.
VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
A minimal codebase for finetuning large multimodal models, supporting llava-1.5/1.6, llava-interleave, llava-next-video, llava-onevision, llama-3.2-vision, qwen-vl, qwen2-vl, phi3-v etc.
【EMNLP 2024🔥】Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
A collection of awesome video generation studies.
This is the official code repository for the paper 'Cross-modality Data Augmentation for End-to-End Sign Language Translation'. Accepted at Findings EMNLP 2023
Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.
Code for the ICLR'22 paper "Improving Non-Autoregressive Translation Models Without Distillation"
Visual Alignment Constraint for Continuous Sign Language Recognition. ( ICCV 2021)
A tool for holistic analysis of language generations systems
SLTUNET: A Simple Unified Model for Sign Language Translation (ICLR 2023)
本项目旨在提供一组工具，帮助数据科学家和机器学习工程师更有效地处理和优化他们的数据集和模型。本工具集能够处理包括但不限于数据不平衡、未标记数据利用、样本难度过滤、以及训练集的动态增强等挑战。
Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.