赵沐宇's picture

赵沐宇

lukeleevi

AI & ML interests

Open-source multimodal experiment workflows. Interested in robust deployment.

Recent Activity

upvoted a paper about 15 hours ago

Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models

upvoted a paper 6 days ago

Comprehensive Benchmarking of Long-Form Speech Generation in Diverse Scenarios

upvoted a paper 6 days ago

3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code

View all activity

Organizations

None yet

liked a model 8 days ago

apps1/medical_teacher_asymmetric

Updated 8 days ago • 1

liked a dataset 10 days ago

ashwanim627/items_raw_lite

Viewer • Updated 10 days ago • 22k • 27 • 1

liked a model 13 days ago

junbrro/n1_5_gr1_cotrain_optionY_dust_fk_temp_b636_bsz128x2_15000_layer12_lr3e-5_A_full_scale_mimic

Updated 13 days ago • 1

liked a model 15 days ago

tencent/Hy-MT2-1.8B

Translation • 2B • Updated 15 days ago • 23.9k • • 1.1k

liked a model 17 days ago

tencent/Hy-MT2-7B

Translation • 8B • Updated 15 days ago • 13.4k • 180

liked a model about 2 months ago

tencent/HY-Embodied-0.5

Image-Text-to-Text • 4B • Updated Apr 14 • 491 • 909

liked a model 2 months ago

openbmb/VoxCPM2

Text-to-Speech • 2B • Updated Apr 16 • 260k • 1.38k