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

由Claude扮演一位专业的股票分析师，通过 Python 脚本获取真实市场数据，结合技术分析和消息面，为用户生成决策看板。

This repository contains code and metadata of How2 dataset

This is the official repo for the paper "LongCat-Flash-Omni Technical Report"

利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.

Automate the process of making money online.

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 Tsin…

[NeurIPS'25 Spotlight] Official implementation of "JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation"

[ICLR 2026] Data Pipeline, Models, and Benchmark for Omni-Captioner.

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

A curated list of papers, tools, and resources on Multi-Token Prediction (MTP) and related techniques in Large Language Models (LLMs), Speech-Language Models (SLMs), and more.

Awesome Unified Multimodal Models

Benchmarking Audio-Visual Social Interactivity in Omni Models

EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video

StreamingVLM: Real-Time Understanding for Infinite Video Streams

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

[CVPR 2026 highlight] Official release of EgoAVU Egocentric Audio-Visual Understanding

The Easy Communications (EasyCom) dataset is a world-first dataset designed to help mitigate the *cocktail party effect* from an augmented-reality (AR) -motivated multi-sensor egocentric world view.

Official implementation of paper VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format

[ICLR 2026] MMDuet2: Enhancing Proactive Interaction of Video MLLMs with Multi-Turn Reinforcement Learning

[CVPR 2025] EgoLife: Towards Egocentric Life Assistant

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Advancing Open-source World Models

An End-to-End Infrastructure for Training and Evaluating Various LLM Agents

World's First Full-Chinese Ray-Ban Meta AI Assistant - 全球首个全中文 Ray-Ban Meta 智能眼镜 AI 助手

An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System