OpenGVLab

community

https://github.com/opengvlab

opengvlab

OpenGVLab

Activity Feed Request to join this org

AI & ML interests

Computer Vision

Recent Activity

CuiLong7 authored a paper 19 days ago

Unlocking the Potential of Image Editing via Concept Scaling and Dense Supervision

CuiLong7 authored a paper 19 days ago

LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model

CuiLong7 authored a paper 19 days ago

ViCO: A Training Strategy towards Semantic Aware Dynamic High-Resolution

View all activity

Papers

Imagine Before You Predict: Interleaved Latent Visual Reasoning for Video Event Prediction

RIVER: A Real-Time Interaction Benchmark for Video LLMs

View all Papers

prithivMLmods

posted an update 2 days ago

Post

369

Scribble-Board-Fast is a sketch-to-image workspace powered by Klein-9B, transforming doodles, brush strokes, stickers, and uploaded images into high-fidelity visuals with 4-step distilled sampling.

> Space: prithivMLmods/Scribble-Board-Fast
> GitHub: https://github.com/PRITHIVSAKTHIUR/Scribble-Board-Fast

> To learn more, visit the app page or the respective model pages.

prithivMLmods

posted an update 10 days ago

Post

3785

VisionGuardrail, a multimodal content-safety classifier based on Qwen3.5, is now available on Hugging Face in 4B and 9B variants. It is a direct upgrade to ImageShield-MMCF, providing improved parental controls through conservative visual content-safety filtering.

More About:
➠ hf.co/blog — https://huggingface.co/blog/prithivMLmods/vision-guardrail-mini-blog

➠ Models:
✦ VisionGuardrail-4B: prithivMLmods/VisionGuardrail-4B
✦ VisionGuardrail-9B: prithivMLmods/VisionGuardrail-9B

➠ Dataset:
✦ ImageShield-Guardrail-Pro: prithivMLmods/ImageShield-Guardrail-Pro

⤷ To learn more, visit the app page or the respective model pages.

prithivMLmods

posted an update 18 days ago

Post

3082

ImageShield-MMCF — Multimodal Content Filter is a multimodal content-safety classifier built on top of Qwen3.5 and is now available on Hugging Face!

This is the preview initial version (v1.0) of the model, designed to classify visual content as Safe or Unsafe, with a particular focus on detecting Not Safe for Work (NSFW) and other potentially sensitive visual content.

The demo is implemented in the prithivMLmods/opencaption-4b-vl-sft Space, which serves as an active content-safety layer for computer vision tasks. It helps block Not Safe for Work (NSFW) content generation and paves the way for more meaningful and responsible creativity.

⊹ ImageShield-MMCF-0.8B: prithivMLmods/ImageShield-MMCF-0.8B
⊹ ImageShield-MMCF-2B: prithivMLmods/ImageShield-MMCF-2B

2 replies

CuiLong7

authored 3 papers 19 days ago

Unlocking the Potential of Image Editing via Concept Scaling and Dense Supervision

Paper • 2608.16812 • Published 29 days ago • 50

LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model

Paper • 2604.20796 • Published Apr 22 • 244

ViCO: A Training Strategy towards Semantic Aware Dynamic High-Resolution

Paper • 2510.12793 • Published Oct 14, 2025 • 5

CuiLong7

submitted a paper to Daily Papers 20 days ago

Unlocking the Potential of Image Editing via Concept Scaling and Dense Supervision

Paper • 2608.16812 • Published 29 days ago • 50

luotto

authored 13 papers 27 days ago

OpenVisTool: An Open Recipe for Synthesizing Instructive Visual Tool-Use Trajectories

Paper • 2608.08557 • Published Aug 9 • 2

Enjoy Your Talk: A Human-Centered Benchmark for Multi-Turn Dialogue with Decoupled User Simulation, Target Modeling, and Judging

Paper • 2607.10428 • Published Jul 24 • 1

Omni-Perception Policy Optimization for Multimodal Emotion Reasoning

Paper • 2606.25325 • Published Jun 24

MER-R1: Multimodal Emotion Reasoning via Slow-Fast Thinking Synergy

Paper • 2606.27652 • Published Jun 26

EgoPro-Bench: Benchmarking Personalized Proactive Interaction in Egocentric Video Streams

Paper • 2605.07299 • Published May 8

ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent Trajectories

Paper • 2606.11520 • Published Jun 9

From Pixels to Words -- Towards Native One-Vision Models at Scale

Paper • 2605.28820 • Published May 27 • 77

GeoSym127K: Scalable Symbolically-verifiable Synthesis for Multimodal Geometric Reasoning

Paper • 2605.16371 • Published May 10

SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture

Paper • 2605.12500 • Published May 12 • 199

OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis

Paper • 2604.15093 • Published Apr 16 • 30

ReinDriveGen: Reinforcement Post-Training for Out-of-Distribution Driving Scene Generation

Paper • 2604.01129 • Published Apr 1 • 8

EVA: Efficient Reinforcement Learning for End-to-End Video Agent

Paper • 2603.22918 • Published Mar 24 • 44

Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe

Paper • 2209.05324 • Published Sep 12, 2022

AI & ML interests

Recent Activity

Papers

Team members 118

OpenGVLab's activity