OpenMMLab Semantic Segmentation Toolbox and Benchmark.

The repository for Springer IJCV 2025 (LR-ASD: Lightweight and Robust Network for Active Speaker Detection)

code repo for LoCoNet: Long-Short Context Network for Active Speaker Detection

The repository for IEEE CVPR 2023 (A Light Weight Model for Active Speaker Detection)

Make any agent harness multimodal-native.

The open-source CapCut alternative

Vision-OPD is a regional-to-global on-policy self-distillation framework that transfers a model's own privileged crop-conditioned perception to its full-image policy, enabling fine-grained visual u…

🚀 AI 全自动短视频引擎 | AI Fully Automated Short Video Engine

tiny vision language model

A Smarter and Faster On-Device AI Brain for Robots

A flexible, high-performance 3D simulator for Embodied AI research.

One Forge, All Skills: A curated skill collection for academic writing and research. 点开即用，按需配置的一站式学术研究skills平台。

Self-supervised learning for spatial perception

InternRobotics' open platform for building generalized navigation foundation models.

Eagle: Frontier Vision-Language Models with Data-Centric Strategies

[AAAI26 Oral] "SM3Det: A Unified Model for Multi-Modal Remote Sensing Object Detection" and [ICML 26] "Unifying Heterogeneous Multi-Modal Remote Sensing Detection Via Language-Pivoted Pretraining"

A Simple Baseline for Video World Models with Memory

Open Source LLM toolkit to build trustworthy LLM applications. TigerArmor (AI safety), TigerRAG (embedding, RAG), TigerTune (fine-tuning)

Post-training scripts and samples for NVIDIA Cosmos ecosystem

1K resolution vision transformers pretrained on 1B human images.

助力搭建你的数字 AI 员工军团 — 多 Agent 一行命令组网协作。Claude Code / Claude Agent SDK / Codex / Grok Build 4 runtime + 8+ 家 LLM（Anthropic / OpenAI / xAI / MiniMax / DeepSeek / GLM / Kimi / 书生 / 小米 MiMo），自带 Web Dashbo…

Heuristic Learning Blog Post

Obsidian desktop plugin: Babylon.js 3D model viewer with multi-model grid, presets, knowledge notes. Supports GLB/GLTF/STL/OBJ/SPLAT.

[ACL 2025 Findings] Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements

High-Quality Voice Cloning TTS for 600+ Languages

Claw-R1: Empowering OpenClaw with Advanced Agentic RL.

短信转发器——监控Android手机短信、来电、APP通知，并根据指定规则转发到其他手机：钉钉群自定义机器人、钉钉企业内机器人、企业微信群机器人、飞书机器人、企业微信应用消息、邮箱、bark、webhook、Telegram机器人、Server酱、PushPlus、手机短信等。包括主动控制服务端与客户端，让你轻松远程发短信、查短信、查通话、查话簿、查电量等。（V3.0 新增）PS.这个APK…

实时互动的GPT数字人技术笔记，不是数字人开源项目

MCore-Bridge: Providing Megatron-Core model definitions for state-of-the-art large language models and making Megatron training as simple as Transformers.