Wei Huang's picture

Wei Huang

AaronHuangWei

·

AI & ML interests

Deep Learning; Efficient AI; Quantization; LLMs

Recent Activity

updated a model about 10 hours ago

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

published a model about 10 hours ago

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

published a model 1 day ago

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

View all activity

Organizations

Collections 1

Papers 17

arxiv:2604.04921

arxiv:2604.04911

arxiv:2603.13405

arxiv:2512.20557

models 54

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

9B • Updated about 10 hours ago

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

9B • Updated 1 day ago • 12

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

9B • Updated 1 day ago • 13

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

Text-to-Video • Updated Mar 4 • 94

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

Text-to-Video • Updated Mar 3 • 100

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

Text-to-Video • Updated Mar 3 • 9

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

Text-to-Video • Updated Mar 3 • 7

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

Text-to-Video • Updated Feb 15 • 11

AaronHuangWei/Wan2.1-T2V-1.3B-NVFP4RealQuant_weightnoly

Text-to-Video • Updated Jan 15 • 29

AaronHuangWei/Wan2.1-T2V-14B-NVFP4RealQuant_weightnoly

Text-to-Video • Updated Jan 15 • 53

datasets 1

AaronHuangWei/Inf-OmniStream-Train

Preview • Updated Feb 25 • 38