🤝 Open to Collab

Muhammad Umair

umair894

7 232 319

AI & ML interests

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

Recent Activity

upvoted a paper 3 days ago

EnvHarness: Awakening Static Worlds for Agent Learning

upvoted a paper 5 days ago

Embodied-Navigator: Point, Think, Memorize, and Align for Efficient Navigation

liked a Space 6 days ago

agent-memory-leaderboard/leaderboard

View all activity

Organizations

liked a Space 6 days ago

Agent Memory Leaderboard

🧠

729

Unified memory evaluation · Results expected August 12.

liked a Space 10 days ago

AX-Ray Leaderboard

🩻

AI/AX Safety Diagnostics and Assessment

liked a model 16 days ago

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

Text Classification • 0.4B • Updated 27 days ago • 5.34k • 58

liked a Space 16 days ago

Prompt Routing

🧭

108

Route prompts with LFM2.5 Encoder on CPU

liked a model 24 days ago

baidu/Unlimited-OCR

Image-Text-to-Text • 3B • Updated 26 days ago • 3.06M • 4.12k

liked a Space 24 days ago

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

⚔

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

liked a Space 25 days ago

Edge Inference Benchmarks

🚀

On-Device benchmarks across devices and models.

liked a Space about 1 month ago

Pulpie

🍊

Clean HTML 20x faster — encoder vs decoder, live

liked 2 Spaces about 2 months ago

LLM Cinema

🎬

109

A small LLM writes, draws & directs original ASCII films

Unlimited OCR

🏆

408

Extract text from images and PDFs instantly

liked a Space 2 months ago

Fast Gemma Challenge

⚡

100

Multi-agent collab to make Gemma go brrr

liked a model 2 months ago

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

Text Generation • 12B • Updated Jun 19 • 490k • 2.85k

liked 3 Spaces 3 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

💬

466

Detect and label objects in images and videos

liked a model 3 months ago

nvidia/LocateAnything-3B

Image-Text-to-Text • 4B • Updated Jun 12 • 101k • 2.95k

liked 2 Spaces 3 months ago

LTX 2.3 Studio

🎬

324

Generate videos from text, images, audio, or style

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

🐠

226

Generate a video from an image and prompt