-
ZJU @aim-uofa
- Hangzhou
-
03:26
(UTC +08:00) - https://z-mu-z.github.io
Highlights
- Pro
Lists (14)
Sort Name ascending (A-Z)
Stars
JVT: Just Video Transformer makes pixel-space video diffusion simple
A unified framework for building, evaluating, and recursively improving embodied agents. 🚀 Code release coming soon.
More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning
Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue
slime is an LLM training framework for RL Scaling.
Make any agent harness multimodal-native.
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
Open-source, local-first conversational AI video editor with a professional multi-track timeline, Agent Skills, MCP integration, and Remotion rendering.
FunASR-powered video transcription, subtitle generation, and LLM-assisted clipping tool with a local Gradio UI.
Framework for evaluating and improving agents
A curated list of AI agents and agentic frameworks for video editing, video production, and video understanding-for-production.
UniRL is a Framework for Unified Multimodal Model Reinforcement Learning
Resume builder for academics and engineers
Lightweight coding agent that runs in your terminal
NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.
"ViMax: Agentic Video Generation (Director, Screenwriter, Producer, and Video Generator All-in-One)"
[CVPR2026] Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching
TVRBench: Target Viewpoint Reproduction Benchmark for Active Spatial Intelligence
A modern GUI client based on Tauri, designed to run in Windows, macOS and Linux for tailored proxy experience
Long-form audio-visual generation evaluation framework.
[SIGGRAPH 2026] AGILE: Hand-Object Interaction Reconstruction from Video via Agentic Generation
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
A MLLM-based agentic system converts a single room image into executable Blender code for 3D room reconstruction.
Skills for Real Engineers. Straight from my .agents directory.
🚀 AI 全自动短视频引擎 | AI Fully Automated Short Video Engine