HYSEN LABS DIRECTORY
Language tag · curated repositories and deep analysis.
Multi-model, DAG-driven parallel AI film generation — the parallel speedup scales with scene independence, generating film scenes simultaneously instead of one by one. Turns the film-generation execution graph from a topological order into a critical-path-optimal schedule; the only engine that models scene narrative dependencies as a DAG and drives parallel scheduling with the CPM algorithm.
Just a VLM Agent Can Play Robots
Inference engine for Intel devices. Serve LLMs, VLMs, Whisper, Kokoro-TTS, Embedding and Rerank models over OpenAI endpoints.
Self-hosted web search skill for AI agents (OpenClaw/Claude Code/Antigravity) via SearxNG
SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
Confusion Matrix in Python: plot a pretty confusion matrix (like Matlab) in python using seaborn and matplotlib
Anime Face Detector using mmdet and mmpose
A set of evolving nodes that streamline the best use practices in ComfyUI.
A refactored and thoroughly localized (Chinese) version of the Generative Agents project, providing Chinese-speaking users with a maintainable base for further experiments or feature extensions.
An in-the-wild benchmark for AI agents in the production harness.
CLI-first orchestration for AI coding agents: run selected agents and models in parallel, compare raw answers, and coordinate review or implementation workflows.
🧠Mindmap of 🗺️Software Architecture, Software engineering: An Overview of Software Terminologies and Concepts.
Code for "Neural 3D Scene Reconstruction with the Manhattan-world Assumption" CVPR 2022 Oral
a free, non-AI python grammar checker 📝✅
Deep Research Agent CognitiveKernel-Pro from Tencent AI Lab. Paper: https://arxiv.org/pdf/2508.00414
Ultra Flash: Scaling Real-Time Streaming Video Generation to High Resolutions
🌍 AppWorld: A Controllable World of Apps and People for Benchmarking Function Calling and Interactive Coding Agent, ACL'24 Best Resource Paper.
A full interactive remote desktop delivered entirely through SSH and displayed directly in your terminal.
This project is dedicated to the implementation and research of Kolmogorov-Arnold convolutional networks. The repository includes implementations of 1D, 2D, and 3D convolutions with different kernels, ResNet-like and DenseNet-like models, training code based on accelerate/PyTorch, as well as scripts for experiments with CIFAR-10 and Tiny ImageNet.
A general framework for distilling human-created multimodal resources into reusable, executable skills that AI agents can browse, compose, and run, validated across diverse domains including web, PowerPoint, Excel, Blender, CAD, Unreal Engine 5, and REAPER-based music production.