1 11 3

Xuankun Rong

XuankunRong

https://xuankunrong.github.io/

XuankunRong

AI & ML interests

Federated Learning, Continual Learning

Recent Activity

updated a dataset 2 days ago

XuankunRong/ScienceQA-backdoor-EasyR1

published a dataset 2 days ago

XuankunRong/ScienceQA-backdoor-EasyR1

updated a dataset 4 days ago

XuankunRong/ScienceQA-clean-EasyR1

View all activity

Organizations

None yet

XuankunRong's activity

updated a dataset 2 days ago

XuankunRong/ScienceQA-backdoor-EasyR1

Viewer • Updated 2 days ago • 8.86k • 31

published a dataset 2 days ago

XuankunRong/ScienceQA-backdoor-EasyR1

Viewer • Updated 2 days ago • 8.86k • 31

updated a dataset 4 days ago

XuankunRong/ScienceQA-clean-EasyR1

Viewer • Updated 4 days ago • 8.24k • 89

published a dataset 4 days ago

XuankunRong/ScienceQA-clean-EasyR1

Viewer • Updated 4 days ago • 8.24k • 89

updated a model 10 days ago

XuankunRong/llava-1-5-7b-iconqa-poison-10

Updated 10 days ago • 9

published 2 models 10 days ago

XuankunRong/llava-1-5-7b-iconqa-poison-10

Updated 10 days ago • 9

XuankunRong/llava-1-5-7b-iconqa-lora

Updated 10 days ago

updated a model 10 days ago

XuankunRong/internvl2-5-8b-iconqa-poison-10

Updated 10 days ago • 1

published 2 models 10 days ago

XuankunRong/internvl-2-5-8b-iconqa-lora

Updated 10 days ago

XuankunRong/internvl2-5-8b-iconqa-poison-10

Updated 10 days ago • 1

published a dataset 10 days ago

XuankunRong/checkpoints

Updated 10 days ago • 38

upvoted a paper 12 days ago

Backdoor Cleaning without External Guidance in MLLM Fine-tuning

Paper • 2505.16916 • Published 12 days ago • 16

commented a paper 12 days ago

Backdoor Cleaning without External Guidance in MLLM Fine-tuning

Paper • 2505.16916 • Published 12 days ago • 16 •

upvoted a paper 15 days ago

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning

Paper • 2505.11049 • Published 19 days ago • 59

upvoted a paper about 1 month ago

FlowReasoner: Reinforcing Query-Level Meta-Agents

Paper • 2504.15257 • Published Apr 21 • 46

updated a dataset about 2 months ago

XuankunRong/scienceqa

Viewer • Updated Apr 18 • 83.9k • 12

published a dataset about 2 months ago

XuankunRong/scienceqa

Viewer • Updated Apr 18 • 83.9k • 12

upvoted a paper about 2 months ago

ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective Layers

Paper • 2504.00502 • Published Apr 1 • 22

upvoted 2 papers 2 months ago

Efficient Inference for Large Reasoning Models: A Survey

Paper • 2503.23077 • Published Mar 29 • 46

Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation

Paper • 2503.19622 • Published Mar 25 • 31