Hugging Apps

Team

community

Activity Feed

AI & ML interests

None defined yet.

Recent Activity

multimodalart updated a Space 34 minutes ago

hugging-apps/chessmamba-play

multimodalart published a Space about 5 hours ago

hugging-apps/mr-pong-rl-demo

multimodalart updated a Space about 6 hours ago

hugging-apps/mr-pong-rl-demo

View all activity

hugging-apps 's Spaces 259

OliveGemma

🫒

Mediterranean & European diet recognition VLM

UniPASE Speech Enhancement

🎙

Universal speech enhancement with high fidelity

GAP-URGENet

🔊

Universal speech enhancement (1st, ICASSP 2026 URGENT)

ID-V2V

🪞

Identity-preserving video restyle & relight

Krea 2 Pose ControlNet

🎨

Generate characters in a pose from a reference image

MiniWorld Simulator

🌍

Drive a video world model with a camera path from one frame

Light Forcing Video Generation

🎬

Text-to-video with Light Forcing sparse attention

SpatioLM Spatial Understanding

🧭

Spatial reasoning VLM demo powered by SpatioLM

PatchAlign3D

🧩

Zero-shot 3D part segmentation from text queries

LoFi-MedG Medical Grounding

🏥

Medical visual grounding and VQA with LoFi-MedG

InVirtuoGen Molecular Generation

🧬

Generate drug-like molecules with discrete flow matching

CodeFuse-SVR-8B

🔍

Structured visual reasoning for screenshots and diagrams

DRIFT DGA Detector

🛡

Classify domain names as Benign or DGA-generated

CVE to MITRE ATT&CK Mapper

🛡

Map CVE descriptions to MITRE ATT&CK techniques

PlagueKind MiniMax H3

🦊

The PlagueKind V1.5 workflow for MiniMax-H3 video + audio

MuScriptor Music Transcription

🎵

Convert music audio to MIDI with MuScriptor

DEFT-RLVR Autonomous Driving VLM

🚗

Autonomous driving scene reasoning with DEFT-RLVR

ReMind Video Generator

🫥

Image-to-video with dynamic memory for out-of-sight events

MoPET Medical Classification

🩺

MoPET mixture-of-experts medical image classification

PixelModel v6

🖼

155M-parameter MMDiT text-to-image model

Lumma-0.6B-Extract

🔍

Structured JSON extraction from text with a 0.6B LLM

Freya-TTS Turkish

🎙

Turkish TTS via 183M flow-matching DiT (48 kHz)

Lift4D

🐐

Text-prompted 4D reconstruction from a casual video

Perceptual Flow Matching

🎨

Few-step image generation with PFM on SD3-Medium