🤝 Open to Collab

Muhammad Umair

umair894

7 228 317

AI & ML interests

Multimodal Reidentification | Feature Upscaling | Cross-modal alignment | robust generalization | PhD UESTC

Recent Activity

liked a model 1 day ago

LiquidAI/LFM2.5-Encoder-350M-Prompt-Router

liked a Space 1 day ago

LiquidAI/prompt-routing

upvoted a paper 2 days ago

WorldClaw: Agentic 3D Open-World Generation at Scale

View all activity

Organizations

liked a model 1 day ago

LiquidAI/LFM2.5-Encoder-350M-Prompt-Router

Text Classification • 0.4B • Updated 12 days ago • 2.03k • 39

liked a Space 1 day ago

Prompt Routing

🧭

Route prompts with LFM2.5 Encoder on CPU

liked a model 9 days ago

baidu/Unlimited-OCR

Image-Text-to-Text • 3B • Updated 12 days ago • 2.89M • 3.98k

liked 2 Spaces 10 days ago

POCKET-26B vs Bonsai · CPU (Gemma4-based)

⚔

BONSAI vs POCKET — 26B Gemma4 MoE out-runs a 27B on CPU

Edge Inference Benchmarks

🚀

On-Device benchmarks across devices and models.

liked a Space 26 days ago

Pulpie

🍊

Clean HTML 20x faster — encoder vs decoder, live

liked 2 Spaces about 1 month ago

LLM Cinema

🎬

109

A small LLM writes, draws & directs original ASCII films

Unlimited OCR

🏆

379

Extract text from images and PDFs instantly

liked a Space about 2 months ago

Fast Gemma Challenge

⚡

100

Multi-agent collab to make Gemma go brrr

liked a model about 2 months ago

yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF

Text Generation • 12B • Updated Jun 19 • 283k • 2.82k

liked 3 Spaces 2 months ago

RF-DETR Realtime Webcam Demo

🎯

Segment objects in live webcam and uploaded media

NV-Generate Synthetic Medical Imaging

🧠

Synthetic 3D CT and MR generation with NVIDIA NV-Generate.

LocateAnything

💬

446

Detect and label objects in images and videos

liked a model 2 months ago

nvidia/LocateAnything-3B

Image-Text-to-Text • 4B • Updated Jun 12 • 426k • 2.89k

liked 2 Spaces 2 months ago

LTX 2.3 Studio

🎬

317

Generate videos from text, images, audio, or style

WAN2.2 I2V LIGHTNING-Video-4-8step

🐠

193

Generate animated video from a single image

liked a model 2 months ago

lintw/HealthGPT-Pro-4B

Image-Text-to-Image • 4B • Updated 9 days ago • 2.34k • 5

liked 3 Spaces 3 months ago

Carbon

🧬

177

Explore DNA model predictions and protein folding interactively

VGGT-Omega Demo

🌀

3D reconstruction from images/video with VGGT-Omega

TIPSv2 Feature Explorer

🔍

Explore TIPSv2 features, segmentations, depth and normals