AI Agent Skills

SALMONN family: A suite of advanced multi-modal LLMs

Run multimodal agents that operate desktop interfaces

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it…

FlowGram is an extensible workflow development framework with built-in canvas, form, variable, and materials that helps developers build AI workflow platforms faster and…

The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.

Official Repo For Pixel-LLM Codebase: Sa2VA (Arxiv-25), SAMTok (CVPR-26), VRT, SaSaSa2VA (1-st solution for LSVOS)

🔥 [ICCV 2025 Highlight] InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity

A 3B-active-parameter native unified multimodal model for image and video understanding, generation, and editing.

Appshark is a static taint analysis platform to scan vulnerabilities in an Android app.

[ICCV 2025] 🔥🔥 UNO: A Universal Customization Method for Both Single and Multi-Subject Conditioning

Bernini is a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer.

vArmor is a cloud-native container hardening system that leverages AppArmor/BPF/Seccomp and network proxy technologies to enforce access control from system calls to app…

[ICLR 2026] Trace Anything: Representing Any Video in 4D via Trajectory Fields

[ICLR 2026]🔥🔥🔥MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement

🔥 [ICCV 2025 Highlight] Official ComfyUI native node supporting InfiniteYou with FLUX

Official implementation of Chain-of-Action: Trajectory Autoregressive Modeling for Robotic Manipulation. Accepted in NeurIPS 2025.