| 1 |
Are Music Foundation Models Better at Singing Voice Deepfake Detection? Far-Better Fuse them with Speech Foundation Models |
提出FIONA框架，融合音乐和语音基础模型，提升歌声Deepfake检测性能。 |
representation learning foundation model |
|
|
| 2 |
FlowRL: Flow-Augmented Few-Shot Reinforcement Learning for Semi-Structured Sensor Data |
FlowRL：利用流增强的少样本强化学习处理半结构化传感器数据 |
reinforcement learning flow matching |
|
|
| 3 |
One-shot World Models Using a Transformer Trained on a Synthetic Prior |
提出基于Transformer的One-Shot World Model，利用合成先验数据进行环境建模。 |
world model |
|
|
| 4 |
Test Time Learning for Time Series Forecasting |
提出基于测试时学习（TTT）模块的并行架构，提升长时序预测性能。 |
Mamba SSM MAE |
|
|