In a Training Loop 🔄

2 10

Masao Taketani

Masao-Taketani

https://medium.com/@masaotaket003

AI & ML interests

Generative Deep Learning (image/simulation/text/audio)

Recent Activity

updated a model 1 minute ago

LiquidAI/LFM2.5-Audio-1.5B-JP

liked a model about 1 hour ago

LiquidAI/LFM2.5-1.2B-JP-202606-ONNX

liked a model about 1 hour ago

LiquidAI/LFM2.5-1.2B-JP-202606-MLX-5bit

View all activity

Organizations

updated a model 1 minute ago

LiquidAI/LFM2.5-Audio-1.5B-JP

Audio-to-Audio • 1B • Updated 1 minute ago • 11 • 5

liked 9 models about 1 hour ago

updated a model about 17 hours ago

LiquidAI/LFM2.5-Audio-1.5B-JP-GGUF

Audio-to-Audio • 1B • Updated about 17 hours ago • 33 • 2

New activity in LiquidAI/LFM2.5-Audio-1.5B-JP-GGUF 4 days ago

Add "in japanese" to the system prompts of ASR and TTS.

#1 opened 4 days ago by

Masao-Taketani

liked a model 3 months ago

LiquidAI/LFM2-24B-A2B

Text Generation • 24B • Updated Mar 30 • 20.1k • 331

commented a paper 5 months ago

Diffusion Models Are Real-Time Game Engines

Paper • 2408.14837 • Published Aug 27, 2024 • 126 •

updated 2 models 5 months ago

Masao-Taketani/vizdoom-finetuned-decoder

Updated Dec 22, 2025

Masao-Taketani/vizdoom-diffusion-dynamic-model

Updated Dec 22, 2025 • 7

updated 2 datasets 5 months ago

Masao-Taketani/vizdoom-inference-pixel-dataset

Viewer • Updated Dec 22, 2025 • 1.52M • 1.02k

Masao-Taketani/vizdoom-inference-latent-dataset

Updated Dec 22, 2025 • 495