Wei Huang's picture

Wei Huang

AaronHuangWei

·

AI & ML interests

Deep Learning; Efficient AI; Quantization; LLMs

Recent Activity

upvoted a paper 5 days ago

Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond

updated a model 12 days ago

AaronHuangWei/streamingomni-sft-stage1-multimodal_compression_streamingonly-ckpt2400-final

published a model 12 days ago

AaronHuangWei/streamingomni-sft-stage1-multimodal_compression_streamingonly-ckpt2400-final

View all activity

Organizations

Collections 1

Papers 17

arxiv:2604.04921

arxiv:2604.04911

arxiv:2603.13405

arxiv:2512.20557

models 56

AaronHuangWei/streamingomni-sft-stage1-multimodal_compression_streamingonly-ckpt2400-final

9B • Updated 12 days ago • 14

AaronHuangWei/streamingomni-sft-stage1-multimodal_compression_streamingonly-ckpt1600-final

9B • Updated 13 days ago • 15

AaronHuangWei/streamingomni-sft-stage1-multimodal_compression_streamingonly-ckpt600-new2

9B • Updated 21 days ago • 18

AaronHuangWei/streamingomni-sft-stage1-multimodal_compression_streamingonly-checkpoint-5000

9B • Updated 22 days ago • 20

AaronHuangWei/streamingomni-sft-stage1-multimodal_compression_mixeddata-checkpoint-2200

9B • Updated 22 days ago • 21

AaronHuangWei/Wan2.1-T2V-14B-NVFP4Fake_layer_4o6

Text-to-Video • Updated Mar 4 • 30

AaronHuangWei/Wan2.1-T2V-14B-NVFP4Fake_layer_4o6_search_n100_s0.001_p2.4

Text-to-Video • Updated Mar 3 • 31

AaronHuangWei/Wan2.2-TI2V-5B-NVFP4Fake_layer_4o6_search_n100_s0.001_p2.4

Text-to-Video • Updated Mar 3 • 10

AaronHuangWei/Wan2.2-TI2V-5B-NVFP4Fake_layer_4o6

Text-to-Video • Updated Mar 3 • 14

AaronHuangWei/Wan2.2-TI2V-5B-NVFP4FakeQuant_ignorelayer

Text-to-Video • Updated Feb 15 • 10

datasets 1

AaronHuangWei/Inf-OmniStream-Train

Preview • Updated Feb 25 • 57