Official code of paper "Speculative Ensemble: Fast Large Language Model Ensemble via Speculation"

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

for fun

[ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

The official repo of continuous speculative decoding

Fast inference from large lauguage models via speculative decoding

Bilibili视频数据爬虫 精确爬取完整的b站视频数据，包括标题、up主、up主id、精确播放数、历史累计弹幕数、点赞数、投硬币枚数、收藏人数、转发人数、发布时间、视频时长、视频简介、作者简介和标签

Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis

Auto Interpretation Pipeline and many other functionalities for Multimodal SAE Analysis.

100+ Chinese Word Vectors 上百种预训练中文词向量

Text classification with Machine Learning methods and Pre-Trained Embedding model on Sogou News Corpus

中文文本分类实践，基于搜狗新闻语料库，采用传统机器学习方法以及预训练模型等方法

本项目主要是采用蒙特卡洛搜索树与残差神经网络实现的一个可在小规模硬 件设施上短期训练一个拥有较强棋力的五子棋 AI。参考 AlphaGo Zero 原始论文 《Mastering the game of Go without human knowledge》实现的一个在五子棋游 戏上的复现，实现过程中采用相应的原创性方法进行改进，使其算法更加适应项 目需求并最终取得的较好的效果。MCTS 部…

Efficient Semantic Image Synthesis via Class-Adaptive Normalization (TPAMI 2021)

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

The code repository for "Wings: Learning Multimodal LLMs without Text-only Forgetting" [NeurIPS 2024]

Official Implementation of Rectified Flow (ICLR2023 Spotlight)

The code repository for "OmniEvalKit: A Modular, Lightweight Toolbox for Evaluating Large Language Model and its Omni-Extensions"

Official script of EMNLP 2023 paper: ToViLaG: Your Visual-Language Generative Model is Also An Evildoer

Implementation of the model used in the paper Protest Activity Detection and Perceived Violence Estimation from Social Media Images (ACM Multimedia 2017)

SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images (AAAI2023)

Repository for Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

[NeurIPS 2024] Official Code for the Paper "Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning"

[EMNLP 2023] Adapting Language Models to Compress Long Contexts

[NAACL 2025 Main] Official Implementation of MLLMU-Bench

This repo lists relevant papers summarized in our survey paper: A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models.

Official code for Guiding Language Model Math Reasoning with Planning Tokens

📰 Must-read papers and blogs on Speculative Decoding ⚡️