3 papers
cs.CV2026
Powerful Teachers Matter: Text-Guided Multi-view Knowledge Distillation with Visual Prior Enhancement
Xin Zhang, Jianyang Xu, Hao Peng +5
Knowledge distillation transfers knowledge from large teacher models to smaller students for efficient inference. While existing methods primarily focus on distillation strategies,…
cs.CL2024
NoisyAG-News: A Benchmark for Addressing Instance-Dependent Noise in Text Classification
Hongfei Huang, Tingting Liang, Xixi Sun +2
Existing research on learning with noisy labels predominantly focuses on synthetic label noise. Although synthetic noise possesses well-defined structural properties, it often fail…
cs.CV2023
PILL: Plug Into LLM with Adapter Expert and Attention Gate
Fangyuan Zhang, Tingting Liang, Zhengyuan Wu +1
Due to the remarkable capabilities of powerful Large Language Models (LLMs) in effectively following instructions, there has been a growing number of assistants in the community to…