👋 Open to Work

十百千

x1001000

·

AI & ML interests

Agentic Robotic Physical

Recent Activity

upvoted a paper 18 days ago

Agensh: Scaling Organizational Intelligence to 1,024 Agents

upvoted a collection 25 days ago

upvoted a collection about 1 month ago

Muse Spark Open

View all activity

Organizations

upvoted a paper 18 days ago

Agensh: Scaling Organizational Intelligence to 1,024 Agents

Paper • 2609.26781 • Published Sep 22 • 23

upvoted a collection 25 days ago

Flora

Flora: An Open Model Suite for Scaling Robotics Data Engines • 3 items • Updated 2 days ago • 50

upvoted a collection about 1 month ago

Muse Spark Open

Muse Spark Open model. A 816B parameter model with 42B Active parameters. BF16 and NVFP4 Weights. • 2 items • Updated Oct 15 • 177

liked 2 Spaces about 1 month ago

Drama 3

Direct Fish Audio Drama 3, streaming on ZeroGPU

Microduck Arena

Race Microduck policies on a clock you can trust

updated a Space 2 months ago

Volleyball Serve Speed Estimator

Estimate volleyball serve speed from a side-view court video

liked 4 Spaces 2 months ago

Microduck Sandbox

Display a bold landing page with stylized title and button

Supertonic 3 (TTS)

Lightning-Fast, On-Device, Multilingual, Accurate TTS

Qwen3-TTS Demo

Clone a voice and synthesize speech from text

Qwen3-TTS Demo

Generate speech from text with voice design, cloning, or presets

upvoted a collection 2 months ago

Qwen-AgentWorld

3 items • Updated Jun 24 • 84

upvoted a collection 3 months ago

Cosmos3

Omnimodal World Models for Physical AI • 6 items • Updated 2 days ago • 221

liked a model 3 months ago

Speech-AI-Research-Center/Breeze-ASR-26

Automatic Speech Recognition • 2B • Updated Apr 21 • 24 • 3

upvoted a collection 3 months ago

Qwen3.8

4 items • Updated Aug 13 • 618

updated a Space 4 months ago

MediaPipe Pose Landmarker

Track 33 body keypoints using MediaPipe

published a Space 4 months ago

Volleyball Serve Speed Estimator

Estimate volleyball serve speed from a side-view court video

liked 2 Spaces 4 months ago

MediaPipe Pose Estimation

Track 33 body keypoints using MediaPipe

SoulX-Singer

Generate singing voice from lyrics or convert voices

liked a model 5 months ago

openbmb/VoxCPM2

Text-to-Speech • 2B • Updated 7 days ago • 979k • 1.79k

liked a Space 5 months ago

VoxCPM Demo

VoxCPM2 Nano-vLLM Demo