2 papers
cs.AI2026
LLM4LLM: Bridging Kernel Benchmarks and Real Deployment via Closed-Loop Agentic Optimization
Hui Zeng, Pengfei Yang, Yanxin Chen +2
Large language models have become increasingly capable agents for low-level code and kernel optimization, but isolated kernel benchmarks provide only a proxy for the deployment beh…
cs.CV2025
MST-Distill: Mixture of Specialized Teachers for Cross-Modal Knowledge Distillation
Hui Li, Pengfei Yang, Juanyang Chen +3
Knowledge distillation as an efficient knowledge transfer technique, has achieved remarkable success in unimodal scenarios. However, in cross-modal settings, conventional distillat…