2 papers
cs.CV2025
Distillation Dynamics: Towards Understanding Feature-Based Distillation in Vision Transformers
Huiyuan Tian, Bonan Xu, Shijian Li
While feature-based knowledge distillation has proven highly effective for compressing CNNs, these techniques unexpectedly fail when applied to Vision Transformers (ViTs), often pe…
cs.LG2025
Kunlun Anomaly Troubleshooter: Enabling Kernel-Level Anomaly Detection and Causal Reasoning for Large Model Distributed Inference
Yuyang Liu, Jingjing Cai, Jiayi Ren +4
Anomaly troubleshooting for large model distributed inference (LMDI) remains a critical challenge. Resolving anomalies such as inference performance degradation or latency jitter i…