IXCLab@Shanghai AI Lab

OpenIXCLab's activity

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

yuhangzang 

authored a paper about 21 hours ago

SeC: Advancing Complex Video Object Segmentation via Progressive Concept Construction

Paper • 2507.15852 • Published 1 day ago • 25

rookiexiong 

authored a paper 1 day ago

SeC: Advancing Complex Video Object Segmentation via Progressive Concept Construction

Paper • 2507.15852 • Published 1 day ago • 25

rookiexiong 

updated a model 1 day ago

OpenIXCLab/SeC-4B

Mask Generation • 4B • Updated 1 day ago • 4 • 4

rookiexiong 

updated a dataset 1 day ago

OpenIXCLab/SeCVOS

Viewer • Updated 1 day ago • 182 • 65 • 3

rookiexiong 

published a dataset 6 days ago

OpenIXCLab/SeCVOS

Viewer • Updated 1 day ago • 182 • 65 • 3

rookiexiong 

published a model 6 days ago

OpenIXCLab/SeC-4B

Mask Generation • 4B • Updated 1 day ago • 4 • 4

yuhangzang 

updated a Space 14 days ago

Running

MMLongBench Doc

🥇

A long-context, multimodal document understanding benchmark

yuhangzang 

published a dataset 14 days ago

OpenIXCLab/mmlongbench-doc-results

Viewer • Updated 14 days ago • 2.16k • 80

yuhangzang 

updated a dataset 14 days ago

OpenIXCLab/mmlongbench-doc-results

Viewer • Updated 14 days ago • 2.16k • 80

yuhangzang 

published a Space 19 days ago

Running

MMLongBench Doc

🥇

A long-context, multimodal document understanding benchmark

yuhangzang 

authored a paper 28 days ago

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing

Paper • 2506.19848 • Published 29 days ago • 26

yuhangzang 

authored a paper about 2 months ago

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings

Paper • 2506.04997 • Published Jun 5

myownskyW7 

authored 6 papers 2 months ago

MMDetection: Open MMLab Detection Toolbox and Benchmark

Paper • 1906.07155 • Published Jun 17, 2019

VideoRoPE: What Makes for Good Video Rotary Position Embedding?

Paper • 2502.05173 • Published Feb 7 • 65

Light-A-Video: Training-free Video Relighting via Progressive Light Fusion

Paper • 2502.08590 • Published Feb 12 • 44

RelightVid: Temporal-Consistent Diffusion Model for Video Relighting

Paper • 2501.16330 • Published Jan 27 • 2

DualToken: Towards Unifying Visual Understanding and Generation with Dual Visual Vocabularies

Paper • 2503.14324 • Published Mar 18 • 2

Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning

Paper • 2505.03318 • Published May 6 • 94

yuhangzang 

authored a paper 2 months ago

Visionary-R1: Mitigating Shortcuts in Visual Reasoning with Reinforcement Learning

Paper • 2505.14677 • Published May 20 • 15

myownskyW7 

authored a paper 2 months ago

Visual Agentic Reinforcement Fine-Tuning

Paper • 2505.14246 • Published May 20 • 32