4 papers
Evolving Cache Schedules for Fast Diffusion Policy Inference
Siying Wang, Kangye Ji, Di Wang +1
Diffusion policies achieve strong visuomotor control by iteratively denoising action chunks, but repeated denoising makes real-time deployment computationally demanding. Cache-base…
Jump-teaching: Combating Sample Selection Bias via Temporal Disagreement
Kangye Ji, Fei Cheng, Zeqing Wang +2
Sample selection is a straightforward technique to combat noisy labels, aiming to prevent mislabeled samples from degrading the robustness of neural networks. However, existing met…
SAMCL: Empowering SAM to Continually Learn from Dynamic Domains with Extreme Storage Efficiency
Zeqing Wang, Kangye Ji, Di Wang +2
Segment Anything Model (SAM) struggles in open-world scenarios with diverse domains. In such settings, naive fine-tuning with a well-designed learning module is inadequate and ofte…
LightCL: Compact Continual Learning with Low Memory Footprint For Edge Device
Zeqing Wang, Fei Cheng, Kangye Ji +1
Continual learning (CL) is a technique that enables neural networks to constantly adapt to their dynamic surroundings. Despite being overlooked for a long time, this technology can…