🔄 In a Training Loop

Jianshu Zhang

Sterzhang

·

https://andyzworks.github.io/

AI & ML interests

Data-Centric AI, Multi-Modal Understanding

Recent Activity

published a dataset about 19 hours ago

Sterzhang/video2skill-bench

updated a dataset about 19 hours ago

Sterzhang/video2skill-bench

upvoted a paper 21 days ago

Scaling Automatic Research Agents via World Models

View all activity

Organizations

New activity in Sterzhang/spacenum-bench 2 months ago

Add dataset card, link to paper and project page

#2 opened 4 months ago by

New activity in Sterzhang/vlm2-bench over 1 year ago

Update README.md

#7 opened over 1 year ago by

commented a paper over 1 year ago

EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning

Paper • 2505.16312 • Published May 22, 2025 • 4 •

New activity in Sterzhang/vlm2-bench over 1 year ago

delete dataset for updated version

#6 opened over 1 year ago by

delete for new update of VLM2Bench image cases

#5 opened over 1 year ago by

delete for new update of VLM2Bench image cases

#4 opened over 1 year ago by

Delete VLM2Bench_VID.tsv

#3 opened over 1 year ago by

commented a paper over 1 year ago

VLM$^2$-Bench: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual Cues

Paper • 2502.12084 • Published Feb 17, 2025 • 35 •

New activity in Sterzhang/vlm2-bench over 1 year ago

refined readme

#2 opened over 1 year ago by

Upload vlm2-bench_dataset.zip

#1 opened over 1 year ago by

commented a paper over 1 year ago

2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining

Paper • 2501.00958 • Published Jan 1, 2025 • 110 •

New activity in luoruipu1/Valley-Instruct-65k almost 2 years ago

How to download all the video?

#1 opened almost 2 years ago by

New activity in lmms-lab/LLaVA-Video-178K almost 2 years ago

Query about how many frames are used to generate each caption?

#7 opened almost 2 years ago by

New activity in Sterzhang/PVIT-3M almost 2 years ago

P-Bench?

#2 opened almost 2 years ago by

machinelearningmonk

New activity in Sterzhang/image-textualization about 2 years ago

update readme with datasheet

#2 opened about 2 years ago by