Models
sensenova-vision
opensensenova/sensenova-vision
A unified vision generation model covering detection, segmentation, depth, and 3D geometry, with open weights and training pipelines.
Topics
Related projects
llava-onevision-21.2kFully open multimodal training framework unifying image, long-video, and spatial understanding, releasing models, datasets, and complete training pipelines for researchers building vision-language systems.
Agent-S12.9kAn open-source computer-use agent framework that completes desktop tasks by seeing the screen and clicking, typing, and scrolling like a human.
MobileAgent9.4kTongyi Lab's family of GUI agents and GUI-Owl foundation models that perceive screens and autonomously operate phones, desktops and browsers to complete multi-step tasks.
VibeVoice56.4kMicrosoft's open-source family of voice AI models, including long-form speech recognition, multi-speaker TTS, and real-time streaming TTS weights.
kronos47.3kAn open-source foundation model for financial candlestick sequences, with pretrained tokenizers and models on Hugging Face plus forecasting and fine-tuning pipelines.
voxcpm41.3kAn open-source 2B tokenizer-free multilingual TTS model for voice design, controllable cloning, and studio-quality synthesis.