Wei Huang's picture

Wei Huang

AaronHuangWei

·

AI & ML interests

Deep Learning; Efficient AI; Quantization; LLMs

Recent Activity

upvoted a paper 10 days ago

OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics

upvoted a paper 17 days ago

LongLive-RAG: A General Retrieval-Augmented Framework for Long Video Generation

submitted a paper 17 days ago

LongLive-RAG: A General Retrieval-Augmented Framework for Long Video Generation

View all activity

Organizations

Collections 1

Papers 17

arxiv:2604.04921

arxiv:2604.04911

arxiv:2603.13405

arxiv:2512.20557

models 52

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

9B • Updated Apr 20 • 2

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

9B • Updated Apr 19 • 3

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

9B • Updated Apr 11 • 3

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

9B • Updated Apr 10 • 3

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

9B • Updated Apr 10 • 3

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

Text-to-Video • Updated Mar 3 • 20

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

Text-to-Video • Updated Mar 3 • 2

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

Text-to-Video • Updated Mar 3 • 2

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

Text-to-Video • Updated Feb 15 • 1

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

Text-to-Video • Updated Jan 15 • 6

datasets 1

AaronHuangWei/Inf-OmniStream-Train

Preview • Updated Feb 25 • 42