Amasia NYU

university

https://www.sainingxie.com/

Activity Feed

AI & ML interests

None defined yet.

Recent Activity

conan1024hao updated a model 10 days ago

Amasia-MLLM/Qwen2.5-VL-3B-GRPO-he-5step-20250303

conan1024hao published a model 10 days ago

Amasia-MLLM/Qwen2.5-VL-3B-GRPO-he-5step-20250303

conan1024hao updated a model 13 days ago

Amasia-MLLM/Qwen2.5-VL-3B-GRPO-zh-5step-20250228

View all activity

Amasia-MLLM's activity

conan1024hao

updated a model 10 days ago

Amasia-MLLM/Qwen2.5-VL-3B-GRPO-he-5step-20250303

Updated 10 days ago • 36

conan1024hao

published a model 10 days ago

Amasia-MLLM/Qwen2.5-VL-3B-GRPO-he-5step-20250303

Updated 10 days ago • 36

conan1024hao

updated a model 13 days ago

Amasia-MLLM/Qwen2.5-VL-3B-GRPO-zh-5step-20250228

Updated 13 days ago • 84

conan1024hao

published a model 13 days ago

Amasia-MLLM/Qwen2.5-VL-3B-GRPO-zh-5step-20250228

Updated 13 days ago • 84

jihanyang

authored a paper 13 days ago

UniTok: A Unified Tokenizer for Visual Generation and Understanding

Paper • 2502.20321 • Published 14 days ago • 29

conan1024hao

updated a dataset 15 days ago

Amasia-MLLM/A-OKVQA

Viewer • Updated 15 days ago • 2.08k • 210

conan1024hao

published a dataset 16 days ago

Amasia-MLLM/A-OKVQA

Viewer • Updated 15 days ago • 2.08k • 210

jihanyang

authored a paper about 1 month ago

SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

Paper • 2501.17161 • Published Jan 28 • 108

conan1024hao

published a dataset about 2 months ago

Amasia-MLLM/GLDv2-images

Updated Jan 19

conan1024hao

updated 2 datasets about 2 months ago

Amasia-MLLM/AmasiaIns-1M

Preview • Updated Jan 25

Amasia-MLLM/Cambrian-Pangea-11M

Updated Jan 24 • 37

jihanyang

authored a paper 3 months ago

Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces

Paper • 2412.14171 • Published Dec 18, 2024 • 24

jihanyang

authored a paper 9 months ago

Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs

Paper • 2406.16860 • Published Jun 24, 2024 • 60

jihanyang

authored 2 papers about 1 year ago

V-IRL: Grounding Virtual Intelligence in Real Life

Paper • 2402.03310 • Published Feb 5, 2024 • 16

PLA: Language-Driven Open-Vocabulary 3D Scene Understanding

Paper • 2211.16312 • Published Nov 29, 2022

AI & ML interests

Recent Activity

Team members 3

Amasia-MLLM's activity