Xuanlong Yu

Xuanlong's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 4 months ago

FakeParts: a New Family of AI-Generated DeepFakes

Paper • 2508.21052 • Published Aug 28, 2025 • 8

upvoted a paper 5 months ago

InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

Paper • 2508.18265 • Published Aug 25, 2025 • 211

upvoted a collection 5 months ago

InternVL3.5

Collection

This collection includes all released checkpoints of InternVL3.5, covering different training stages (e.g., Pretraining, SFT, MPO, Cascade RL). • 54 items • Updated Sep 28, 2025 • 104

liked 2 Spaces 5 months ago

Running

Featured

620

The Tokenizer Playground

📝

620

Experiment with and compare different tokenizers

Runtime error

Featured

1.1k

GFPGAN

😁

1.1k

Enhance and restore old photos and AI-generated faces

liked a dataset 7 months ago

ENSTA-U2IS/miniMUAD

Viewer • Updated Jan 6, 2025 • 1.7k • 85 • 1

upvoted an article 7 months ago

view article

Article

nanoVLM: The simplest repository to train your VLM in pure PyTorch

• 
• 
• +5

May 21, 2025

•

247

liked 2 Spaces 8 months ago

Running

Featured

160

SmolVLM realtime WebGPU

⚡

160

Start camera to get descriptions based on instructions

Running

Featured

1.03k

Can You Run It? LLM version

🚀

1.03k

Determine GPU requirements for running large language models

liked a Space 9 months ago

Running on Zero

Featured

343

Describe Anything

⚡

343

Describe masked parts of images

liked 2 models 9 months ago

HuggingFaceTB/SmolVLM-256M-Instruct

Image-Text-to-Text • 0.3B • Updated Apr 8, 2025 • 88.4k • 329

HuggingFaceTB/SmolVLM-256M-Base

Image-to-Text • 0.3B • Updated Jan 20, 2025 • 1.93k • 18

liked 2 Spaces 10 months ago

Runtime error

51

HSMR

💀

51

Convert images of humans to biomechanically accurate 3D skeletons

Running

Featured

365

Qwen2.5 Omni 7B Demo

🏆

365

Generate text and speech responses from text, audio, images, or video input

upvoted an article 11 months ago

view article

Article

SmolVLM Grows Smaller – Introducing the 256M & 500M Models!

• 
• 
• +1

Jan 23, 2025

•

189

liked a Space 11 months ago

Runtime error

Featured

53

Compare Siglip1 Siglip2

🚀

53

Compare SigLIP1 and SigLIP2 on zero shot classification

upvoted an article 11 months ago

view article

Article

SigLIP 2: A better multilingual vision language encoder

• 
• 
• +1

Feb 21, 2025

•

194

liked 3 models about 1 year ago

qnguyen3/nanoLLaVA

Text Generation • 1B • Updated Oct 27, 2024 • 17.3k • 155

NexaAI/OmniVLM-968M

0.5B • Updated Aug 20, 2025 • 1.65k • 529

Qwen/QwQ-32B-Preview

Text Generation • 33B • Updated Jan 12, 2025 • 7.44k • • 1.74k