xiangan's picture

xiangan

xiangan

·

https://anxiangsir.github.io/

anxiangsir

AI & ML interests

None yet

Recent Activity

published a model 3 days ago

mvp-lab/LLaVA-OV-1.5-8B-RL

upvoted an article 4 days ago

Transformers v5: Simple model definitions powering the AI ecosystem

upvoted a paper 4 days ago

SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overhead

View all activity

Organizations

commented a paper 30 days ago

Cambrian-S: Towards Spatial Supersensing in Video

Paper • 2511.04670 • Published about 1 month ago • 36 •

New activity in lmms-lab/LLaVA-558K-Webdataset about 2 months ago

Is this the same dataset as the one stated in the paper?

#1 opened about 2 months ago by

New activity in mvp-lab/LLaVA-OneVision-1.5-Instruct-Data about 2 months ago

SFT is fully uploaded and available. If you encounter missing images or broken links, please report them — we will fix issues on a rolling basis.

#10 opened about 2 months ago by

New activity in lmms-lab/LLaVA-OneVision-1.5-Mid-Training-Webdataset-Quick-Start-3M about 2 months ago

3M stands for what ?

#2 opened about 2 months ago by

New activity in mvp-lab/LLaVA-OneVision-1.5-Mid-Training-85M about 2 months ago

Question about recent dataset updates

#4 opened about 2 months ago by

New activity in lmms-lab/LLaVA-OneVision-1.5-8B-Instruct 2 months ago

Improve model card: Add paper, project page, and code links

#3 opened 2 months ago by

New activity in lmms-lab/LLaVA-OneVision-1.5-4B-Instruct 2 months ago

Improve model card: add prominent links, comprehensive guides, and project details

#2 opened 2 months ago by

New activity in mvp-lab/LLaVA-OneVision-1.5-Instruct-Data 2 months ago

Improve dataset card: Add task categories, tags, paper/code links, and sample usage

#4 opened 2 months ago by

New activity in lmms-lab/LLaVA-OneVision-1.5-4B-Base 2 months ago

Improve model card: Add paper/code/demo links, sample usage, update title & citations

#1 opened 2 months ago by

commented 3 papers 2 months ago

LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training

Paper • 2509.23661 • Published Sep 28 • 46 •

LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training

Paper • 2509.23661 • Published Sep 28 • 46 •

LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training

Paper • 2509.23661 • Published Sep 28 • 46 •

New activity in lmms-lab/LLaVA-OneVision-1.5-Mid-Training-Webdataset-Quick-Start-3M 3 months ago

Update .nv-meta/split.yaml

#1 opened 3 months ago by

New activity in DeepGlint-AI/rice-vit-large-patch14-560 4 months ago

Add `library_name` to metadata and update Github link

#1 opened 4 months ago by

commented 2 papers 4 months ago

Region-based Cluster Discrimination for Visual Representation Learning

Paper • 2507.20025 • Published Jul 26 • 19 •

Region-based Cluster Discrimination for Visual Representation Learning

Paper • 2507.20025 • Published Jul 26 • 19 •

New activity in DeepGlint-AI/MLCD-Seg 7 months ago

Update README.md

#1 opened 7 months ago by

New activity in DeepGlint-AI/llava-mlcd-qwen2.5-7b 7 months ago

Improve language tag

#1 opened 7 months ago by

New activity in DeepGlint-AI/MLCD-Embodied-7B 7 months ago

Improve language tag

#1 opened 7 months ago by

New activity in DeepGlint-AI/mlcd-vit-bigG-patch14-224 8 months ago

Update config.json

#1 opened 8 months ago by