Hongyang Wei

nonwhy

·

nonwhy

AI & ML interests

multimodal large language models & low-level vision

Recent Activity

upvoted a paper 4 days ago

PaDoc: Layout-Grounded Parallel Decoding for Document Parsing

upvoted a paper 19 days ago

Self Gradient Forcing: Native Long Video Extrapolation

upvoted a paper 5 months ago

Generation Enhances Understanding in Unified Multimodal Models via Multi-Representation Generation

View all activity

Organizations

Papers 3

arxiv:2508.03320

arxiv:2506.02161

arxiv:2503.11073

spaces 1

AutoTrain Advanced

models 3

nonwhy/extract_balance_dir_par_seq_r1_roleplaying_grm_base

Updated Jun 10, 2025 • 6

nonwhy/extract_balance_dir_par_seq_r1_roleplaying

Updated Jun 6, 2025 • 3

nonwhy/PURE

Image-to-Image • 7B • Updated Apr 14, 2025 • 42 • 1

datasets 0

None public yet