Open to Collab

Muhammad Umair

umair894

AI & ML interests

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

Recent Activity

upvoted a paper 2 days ago

Geometry-Guided Reinforcement Learning for Multi-view Consistent 3D Scene Editing

upvoted a paper 2 days ago

OpenClaw-RL: Train Any Agent Simply by Talking

upvoted a paper 4 days ago

LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory

View all activity

Organizations

liked a model 15 days ago

Tongyi-MAI/Z-Image-Turbo

Text-to-Image • Updated Jan 30 • 969k • • 4.25k

liked 2 models 25 days ago

Qwen/Qwen3-8B

Text Generation • 8B • Updated Jul 26, 2025 • 8.12M • • 985

Qwen/Qwen3-8B-FP8

Text Generation • 8B • Updated Jul 26, 2025 • 239k • 58

liked a model about 1 month ago

zai-org/GLM-OCR

Image-to-Text • Updated 2 days ago • 2.61M • • 1.19k

liked a Space about 1 month ago

3D Arena

🏢

391

Vote for generative 3D creations and see rankings

liked 4 Spaces about 2 months ago

Waypoint 1 Small

🎮

Explore and navigate through AI-generated worlds in real-time

SAMTok

🎨

SAMTok provides a unified mask-token interface for MLLMs.

Dream-wan2-2-faster-Pro

🎥

1.32k

generate a video from an image with a text prompt

2025 China AI Timeline

📈

Explore 2025 Chinese AI model releases in a timeline

liked 2 Spaces 2 months ago

Qwen Edit Any Pose

🕺

250

Edit any pose with Qwen Edit 2511 Any Pose LoRA

HY-Motion-1.0

💃

252

Text-to-3D and Image-to-3D Generation

liked 2 Spaces 3 months ago

Mapanything Gradio

🐠

117

Convert images to 3D models and depth maps

WindowSeat Reflection Removal

🪟

Remove reflections from photos instantly

liked a model 3 months ago

google/functiongemma-270m-it

Text Generation • Updated Jan 14 • 37.6k • 927

liked 4 Spaces 3 months ago

CUGA Agent

🤖

Configurable Generalist Agent, leader in AppWorld Benchmark

OutofLipSync

💋

Translate and Lipsync any video clips to English

AnyTalker

🎬

Let your character interact naturally

Anim Lab AI

🔥

129

Turn boring math into engaging animation videos

liked 2 models 3 months ago

microsoft/VibeVoice-Realtime-0.5B

Text-to-Speech • 1B • Updated Dec 12, 2025 • 290k • 1.14k

IDEA-Research/RexSeek-3B

Image-Text-to-Text • 4B • Updated Mar 14, 2025 • 130 • 10