Jingdi Lei

huaXiaKyrie

·

https://kyrielei.github.io/

jingdi-lei-44540b2b6

AI & ML interests

Large Language Models, Reinforecement Learning

Recent Activity

updated a model 2 days ago

huaXiaKyrie/delta-Vision-Embedding-Adapter

liked a dataset 3 days ago

huaXiaKyrie/pixmo-ama-train

authored a paper 4 days ago

Just MLPs: Efficient Visual State Reconstruction for Multimodal Language Models

View all activity

Organizations

Papers 7

arxiv:2609.34972

arxiv:2606.02437

arxiv:2605.13779

arxiv:2605.12357

spaces 1

Med

Generate descriptive text from an image and question

models 2

huaXiaKyrie/delta-Vision-Embedding-Adapter

Visual Question Answering • Updated 2 days ago • 4

huaXiaKyrie/Qwen2-VL-MedCaption2

Image-Text-to-Text • 8B • Updated Mar 30, 2025 • 6 • 1

datasets 12

huaXiaKyrie/pixmo-ama-train

Viewer • Updated 4 days ago • 11.2k • 117 • 1

huaXiaKyrie/up

Updated May 22 • 15

huaXiaKyrie/delta-mem-qasper-data

Viewer • Updated May 17 • 2.22k • 42

huaXiaKyrie/memorydataset

Viewer • Updated Apr 16 • 1.2M • 2

huaXiaKyrie/deltalora-memory-multisource-seed42

Updated Mar 26 • 18

huaXiaKyrie/Mem

Preview • Updated Mar 18 • 9

huaXiaKyrie/Plug-and-Play

Preview • Updated Mar 17 • 31

huaXiaKyrie/Med_SFT

Viewer • Updated Apr 7, 2025 • 272k • 494 • 2

huaXiaKyrie/QA_reflection

Viewer • Updated Apr 6, 2025 • 13k • 13 • 1

huaXiaKyrie/Vison_med_vqa

Viewer • Updated Apr 5, 2025 • 5.5k • 28

View 12 datasets