arxiv:2505.11107
許湛然
Splend1dchan
AI & ML interests
Natural Language Processing
Multimodal Representation Learning
Organizations
models 85
Splend1dchan/Taiwanese-Whisper
Automatic Speech Recognition • Updated
• 1
Splend1dchan/byt5lephone_g2p_v1-1024-NMSQA
Question Answering • Updated
• 1
Splend1dchan/h-p-test
Text Generation • Updated
• 3
Splend1dchan/ViT-H-14-laion2B-s32B-b79K
Zero-Shot Image Classification • Updated
• 4 • 1
Splend1dchan/bert-base-uncased-slue-goldtrascription-e3-lr1e-4
Text Classification • 0.1B • Updated
• 3
Splend1dchan/canine-c-squad
Question Answering • 0.1B • Updated
• 12
Splend1dchan/wav2vecu2-t5lephone-small-NMSQA
Updated
Splend1dchan/g2p-t5lephone-small_textsquad
Updated
Splend1dchan/wav2vecu2-t5lephone-small-extractive
Updated
Splend1dchan/t5-large-squad
Updated
• 2
datasets 32
Splend1dchan/AF-Think-audios
Viewer
• Updated
• 1.2k • 1.86k
Splend1dchan/Breezyvoice_MOS4
Viewer
• Updated
• 47 • 47
Splend1dchan/Breezyvoice_MOS3
Viewer
• Updated
• 47 • 12
Splend1dchan/Breezyvoice_MOS2
Viewer
• Updated
• 47 • 8
Splend1dchan/Breezyvoice_MOS
Viewer
• Updated
• 47 • 9
Splend1dchan/tempspiritlm
Viewer
• Updated
• 9 • 10
Splend1dchan/salmon-copy
Viewer
• Updated
• 3.2k • 10
Splend1dchan/MMMU_descriptive
Viewer
• Updated
• 900 • 765
Splend1dchan/gpqa_diamond_visual_noise
Viewer
• Updated
• 198 • 607
Splend1dchan/MMLU_visual_noise
Viewer
• Updated
• 14k • 15