arxiv:2609.38658
🤝 Open to Collab
Jian Chen
puar-playground
AI & ML interests
Audio AI, Document Intelligence, Large language models, MultiModal models, Diffusion models
Recent Activity
authored a paper 4 days ago
Tacit-TTS: From Autoregressive Decoding to Masked Prediction for Efficient Transcript-Free Voice Cloning submitted a paper 4 days ago
Tacit-TTS: From Autoregressive Decoding to Masked Prediction for Efficient Transcript-Free Voice CloningOrganizations
None yet
models 8
puar-playground/btc-chord
Updated • 1.31k
puar-playground/bs-roformer
Updated • 178
puar-playground/htdemucs
Updated • 26 • 1
puar-playground/Phi-3-MusiX
Image-Text-to-Text • Updated • 37 • 1
puar-playground/Col-Phi-3-V
Updated • 8
puar-playground/Col-InternVL2-4B
Updated • 17
puar-playground/TextLap-COCO
Text Generation • Updated • 21
puar-playground/TextLap-Graphic
Text Generation • Updated • 24 • 1
datasets 6
puar-playground/MusiXQA
Preview • Updated • 117 • 3
puar-playground/memory_papers
Updated • 4
puar-playground/VisR-Bench
Viewer • Updated • 5.8k • 61 • 2
puar-playground/crello-cap
Viewer • Updated • 18.2k • 57
puar-playground/MMR
Viewer • Updated • 2k • 18 • 2
puar-playground/LACE
Viewer • Updated • 3 • 17 • 1