yaolinli

ppt-master. AI generates a real, editable PowerPoint from any document — native shapes & animations, editable charts & tables you can change the data on, speaker notes voiced as audio narration, and the option to follow your own .pptx template, not slide images · by Hugo He

BloodArena. JavaScript

claw-eval. Claw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans.

TimeChat-Online. [ACM MM 2025] TimeChat-online: 80% Visual Tokens are Naturally Redundant in Streaming Videos

TimeChat-Captioner. [ICML 2026] Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions

PaperBanana. PaperBanana: Automating Academic Illustration For AI Scientists

Being-H. Being-H is BeingBeyond's family of human-centric embodied foundation models.

sam-audio. The repository provides code for running inference with the Meta Segment Anything Audio Model (SAM-Audio), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

MiMo-V2-Flash. MiMo-V2-Flash: Efficient Reasoning, Coding, and Agentic Foundation Model

StoryMem. Official code for StoryMem: Multi-shot Long Video Storytelling with Memory

MLLM-Token-Compression. Towards Efficient Multimodal Large Language Models: A Survey on Token Compression

pyecharts. 🎨 Python Echarts Plotting Library

OmniVinci. OmniVinci is an omni-modal LLM for joint understanding of vision, audio, and language.

CapRL. [ICLR 2026] An official implementation of "CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning"

Qwen3-Omni. Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.

Awesome-RL-for-Multimodal-Foundation-Models. 📖 This is a repository for organizing papers, codes and other resources related to Visual Reinforcement Learning.

RICO. Official implementation of the paper: [EMNLP 2025] RICO: Improving Accuracy and Completeness in Image Recaptioning via Visual Reconstruction

LightCompress. [EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLMs, VLMs, and video generative models.

video-SALMONN-2. video-SALMONN 2 is a powerful audio-visual large language model (LLM) that generates high-quality audio-visual video captions, which is developed by the Department of Electronic Engineering at Tsinghua University and ByteDance.

SurveyX. Academic Survey Paper Generation.

Awesome-Collection-Token-Reduction. A collection of token reduction (token pruning, merging, clustering, etc.) techniques for ML/AI

EchoInk. EchoInk-R1: Exploring Audio-Visual Reasoning in Multimodal LLMs via Reinforcement Learning (🔥The Exploration of R1 for General Audio-Visual Reasoning with Qwen2.5-Omni)

HumanOmniV2. Python

DeCo. Code for DeCo: Decoupling token compression from semanchc abstraction in multimodal large language models

Long-RL. Long-RL: Scaling RL to Long Sequences (NeurIPS 2025)

Pixel-Reasoner. Pixel-Level Reasoning Model trained with RL [NeuIPS25]

MiniCPM-V. A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone

VDEdit. [ACM MM 2024] Edit As You Wish: Video Caption Editing with Multi-grained User Control

LongVALE. LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos. (CVPR 2025))

video-t3. [ICLR 2025] "Temporal Reasoning Transfer from Text to Video", Lei Li, Yuanxin Liu, Linli Yao, Peiyuan Zhang, Chenxin An, Lean Wang, Xu Sun, Lingpeng Kong, Qi Liu

Seed1.5-VL. Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning, achieving state-of-the-art performance on 38 out of 60 public benchmarks.

VideoRoPE. [ICML 2025 Oral] An official implementation of VideoRoPE & VideoRoPE++

Awesome-LLMs-for-Video-Understanding. 🔥🔥🔥 [IEEE TCSVT] Latest Papers, Codes and Datasets on Vid-LLMs.

smolvlm-realtime-webcam. Real-time webcam demo with SmolVLM and llama.cpp server

livecc. LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale (CVPR 2025)

MiMo. MiMo: Unlocking the Reasoning Potential of Language Model – From Pretraining to Posttraining

Aria-UI. Open-sourced, Fast and Context-aware Action Grounding from GUI Instructions for GUI/Computer-use Agents

GenS. [ACL 2025 Findings] GenS: Generative Frame Sampler for Long Video Understanding

Qwen2.5-Omni. Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.

Time-R1. R1-like Video-LLM for Temporal Grounding

VideoChat-Online. [CVPR 2025] Online Video Understanding: OVBench and VideoChat-Online

VideoMMMU. Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos

Qwen3-VL. Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

HourVideo. [NeurIPS 2024] Official code for HourVideo: 1-Hour Video Language Understanding

Awesome-Token-Compress. A paper list of some recent works about Token Compress for Vit and VLM

Aria. Codebase for Aria - an Open Multimodal Native MoE

LongVideoBench. [Neurips 24' D&B] Official Dataloader and Evaluation Scripts for LongVideoBench.

Movie101. Narrative movie understanding benchmark

gpu_lurker. 服务器 GPU 监控程序，当 GPU 属性满足预设条件时通过微信发送提示消息

Groma. [ECCV2024] Grounded Multimodal Large Language Model with Localized Visual Tokenization

prismatic-vlms. A flexible and efficient codebase for training visually-conditioned language models (VLMs)

lmms-eval. One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

TimeChat. [CVPR 2024] TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding

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

Qwen-Agent. Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

mPLUG-Owl. mPLUG-Owl: The Powerful Multi-modal Large Language Model Family

CapEnrich. Python

CPT. CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation

GLM-130B. GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)

ai-deadlines. :alarm_clock: AI conference deadline countdowns

MMTG. [ACM MM 2022] (Oral): Multi-Modal Experience Inspired AI Creation

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Video-Swin-Transformer. This is an official implementation for "Video Swin Transformers".

clipscore. CLIPScore EMNLP code

video_captioning_datasets. Summary about Video-to-Text datasets. This repository is part of the review paper *Bridging Vision and Language from the Video-to-Text Perspective: A Comprehensive Review*

IDC. Python

Youmakeup_Challenge2022. Python

PDVC. End-to-End Dense Video Captioning with Parallel Decoding (ICCV 2021)

PromptPapers. Must-read papers on prompt-based tuning for pre-trained language models.

X-VLM. X-VLM: Multi-Grained Vision Language Pre-Training (ICML 2022)

bua-extract-feature. Jupyter Notebook

bottom-up-attention.pytorch. A PyTorch reimplementation of bottom-up-attention models

bottom-up-attention. Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome

conceptual-captions. Conceptual Captions is a dataset containing (image-URL, caption) pairs designed for the training and evaluation of machine learned image captioning systems.

CLIP. CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

video-paragraph. Codes for paper "Towards Diverse Paragraph Captioning for Untrimmed Videos". CVPR 2021

SongNet. Code for ACL 2020 paper "Rigid Formats Controlled Text Generation"：https://www.aclweb.org/anthology/2020.acl-main.68/

awesome-vision-language-pretraining-papers. Recent Advances in Vision and Language PreTrained Models (VL-PTMs)

Youmakeup_Baseline. Python

tirg. deep learning, image retrieval, vision and language

YouMakeup.

sms-tools. Sound analysis/synthesis tools for music applications

Music-Project. Project for music

aiclass. for AI class in RUC