Hugging Apps

community

AI & ML interests

None defined yet.

Recent Activity

multimodalart published a Space about 5 hours ago

hugging-apps/dr-mv3d

multimodalart updated a Space about 5 hours ago

hugging-apps/dr-mv3d

multimodalart published a Space about 5 hours ago

hugging-apps/j33-jev

View all activity

published a Space about 5 hours ago

DR-MV3D

Multi-view 3D spatial VQA with dense reward

updated a Space about 5 hours ago

DR-MV3D

Multi-view 3D spatial VQA with dense reward

published a Space about 5 hours ago

J33-Jev · typed decisions

Calibrated typed decisions from a case + question schema

updated a Space about 5 hours ago

J33-Jev · typed decisions

Calibrated typed decisions from a case + question schema

in hugging-apps/moss-image-8-step-dmd about 8 hours ago

Use the distilled LoRA at 0.7 on the base model with v-space Euler sampling

#1 opened 1 day ago by

published a Space about 8 hours ago

MOSS-Image Base 8-step DMD

8-step DMD text-to-image distillation of MOSS-Image-Base

updated 2 Spaces about 8 hours ago

MOSS-Image Base 8-step DMD

8-step DMD text-to-image distillation of MOSS-Image-Base

MOSS-Image 8-step DMD

8-step DMD text-to-image distillation of MOSS-Image-SFT

published a Space about 18 hours ago

Ahenk - Türkçe TTS

Turkish speech in one designed voice, 6 emotions + laughter

updated a Space about 18 hours ago

Ahenk - Türkçe TTS

Turkish speech in one designed voice, 6 emotions + laughter

published a Space about 24 hours ago

Qwen-Image-SP

Structured-prompt scaling for Qwen-Image

published 3 Spaces 1 day ago

DK-VLM — Geometry as Position

Spatial reasoning over video using 3D geometry as position

REKI 2B

VLA model predicting robot action chunks from images

ERVLA

Camera views + instruction → robot action chunks

updated 2 Spaces 1 day ago

DK-VLM — Geometry as Position

Spatial reasoning over video using 3D geometry as position

REKI 2B

VLA model predicting robot action chunks from images

published a Space 1 day ago

Fast-VLA

Fast-VLA robot policy - think once, act fast

updated 3 Spaces 1 day ago

ERVLA

Camera views + instruction → robot action chunks

Fast-VLA

Fast-VLA robot policy - think once, act fast

Qwen-Image-SP

Structured-prompt scaling for Qwen-Image