Ilya Pereverzin

NodeLinker's activity

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

liked 2 models about 1 hour ago

huihui-ai/Qwen2.5-VL-7B-Instruct-abliterated

Image-Text-to-Text • 8B • Updated Nov 7, 2025 • 1.84k • 40

Comfy-Org/Qwen-Image_ComfyUI

Updated 30 days ago • 2.29M • 361

upvoted a collection about 5 hours ago

Qwen3-abliterated

Collection

32 items • Updated Dec 22, 2025 • 46

liked a model about 12 hours ago

jetjodh/sam3

Mask Generation • 0.9B • Updated Nov 25, 2025 • 605 • 7

liked a dataset about 14 hours ago

deepghs/AnimeText

Updated Oct 10, 2025 • 317 • 5

liked a model about 14 hours ago

deepghs/AnimeText_yolo

Object Detection • Updated Oct 10, 2025 • 9

liked a Space about 14 hours ago

Running

3

Manga Translator

📖

3

Translate manga panels into different languages while preserving text style

upvoted a paper about 14 hours ago

LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR

Paper • 2601.14251 • Published 18 days ago • 24

upvoted 3 collections about 14 hours ago

PaddleOCR-VL

Collection

Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model • 3 items • Updated Dec 16, 2025 • 26

PaddleOCR-VL-1.5

Collection

Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing • 5 items • Updated 8 days ago • 8

LightOnOCR-2 🦉

Collection

LightOnOCR-2-1B: a lightweight high-performance end-to-end OCR model family • 12 items • Updated 17 days ago • 22

New activity in stepfun-ai/Step-3.5-Flash 1 day ago

Question about Step 3.5 Flash Base model weights release

1

#21 opened 1 day ago by

NodeLinker

upvoted a collection 1 day ago

Step-3.5-Flash

Collection

step 3.5 models • 5 items • Updated about 6 hours ago • 24

New activity in tencent/Youtu-VL-4B-Instruct 1 day ago

[Urgent Suggestion] Complete Deployment Guide: SDPA Patch (2x speed), 4-bit Fix for 8GB GPUs & Visual Examples

#6 opened 1 day ago by

NodeLinker

New activity in tencent/Youtu-VL-4B-Instruct 2 days ago

Fixing line break & Critical feedback on missing features (OD/Segmentation)

11

#5 opened 3 days ago by

NodeLinker

New activity in tencent/Youtu-VL-4B-Instruct 3 days ago

Fixing a line break error in Python.

#4 opened 3 days ago by

NodeLinker

upvoted 2 papers 3 days ago

Youtu-VL: Unleashing Visual Potential via Unified Vision-Language Supervision

Paper • 2601.19798 • Published 11 days ago • 41

Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models

Paper • 2512.24618 • Published Dec 31, 2025 • 147

upvoted a collection 3 days ago

Youtu

Collection

13 items • Updated 2 days ago • 23

upvoted a paper 3 days ago

VLM-FO1: Bridging the Gap Between High-Level Reasoning and Fine-Grained Perception in VLMs

Paper • 2509.25916 • Published Sep 30, 2025 • 6