Wei Huang

AaronHuangWei

·

AI & ML interests

Deep Learning; Efficient AI; Quantization; LLMs

Recent Activity

authored a paper about 5 hours ago

JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion

authored a paper about 5 hours ago

Reinforcing Dual-Path Reasoning in Spatial Vision Language Models

authored a paper about 5 hours ago

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

View all activity

Organizations

Collections 1

Papers 25

arxiv:2608.03974

arxiv:2606.17539

arxiv:2606.09826

arxiv:2606.02553

models 52

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

9B • Updated Apr 20 • 6

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

9B • Updated Apr 19 • 5

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

9B • Updated Apr 11 • 6

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

9B • Updated Apr 10 • 5

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

9B • Updated Apr 10 • 5

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

Text-to-Video • 14B • Updated Mar 3 • 13

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

Text-to-Video • Updated Mar 3 • 20

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

Text-to-Video • Updated Mar 3 • 18

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

Text-to-Video • Updated Feb 15 • 17

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

Text-to-Video • 0.8B • Updated Jan 15 • 15

datasets 1

AaronHuangWei/Inf-OmniStream-Train

Preview • Updated Feb 25 • 283