6 papers
Learning Expressive Random Feature Models via Parametrized Activations
Zailin Ma, Jiansheng Yang, Yaodong Yang
The random feature (RF) method is a powerful kernel approximation technique, but it typically uses fixed activation functions, limiting its adaptability across diverse tasks. To ov…
RMBench: Memory-Dependent Robotic Manipulation Benchmark with Insights into Policy Design
Tianxing Chen, Yuran Wang, Mingleyang Li +16
Robotic manipulation policies have made rapid progress in recent years, yet most existing approaches give limited consideration to memory capabilities. Consequently, they struggle…
Diagnosing Generalization Failures from Representational Geometry Markers
Chi-Ning Chou, Artem Kirsanov, Yao-Yuan Yang +1
Generalization, the ability to perform well beyond the training context, is a hallmark of biological and artificial intelligence, yet anticipating unseen failures remains a central…
MVR: Multi-view Video Reward Shaping for Reinforcement Learning
Lirui Luo, Guoxi Zhang, Hongming Xu +3
Reward design is of great importance for solving complex tasks with reinforcement learning. Recent studies have explored using image-text similarity produced by vision-language mod…
On the Generalization Properties of Learning the Random Feature Models with Learnable Activation Functions
Zailin Ma, Jiansheng Yang, Yaodong Yang
This paper studies the generalization properties of a recently proposed kernel method, the Random Feature models with Learnable Activation Functions (RFLAF). By applying a data-dep…
Falcon: Fast Visuomotor Policies via Partial Denoising
Haojun Chen, Minghao Liu, Chengdong Ma +8
Diffusion policies are widely adopted in complex visuomotor tasks for their ability to capture multimodal action distributions. However, the multiple sampling steps required for ac…