4 papers
Retrieve, Integrate, and Synthesize: Spatial-Semantic Grounded Latent Visual Reasoning
Jin Cui, Xinyue Long, Xunyong Zhang +5
Multimodal Large Language Models (MLLMs) have made remarkable progress on vision-language reasoning, yet most methods still compress visual evidence into discrete textual thoughts,…
SelecTKD: Selective Token-Weighted Knowledge Distillation for LLMs
Haiduo Huang, Jiangcheng Song, Yadong Zhang +1
Knowledge distillation (KD) is a standard route to compress Large Language Models (LLMs) into compact students, yet most pipelines uniformly apply token-wise loss regardless of tea…
KernelDNA: Dynamic Kernel Sharing via Decoupled Naive Adapters
Haiduo Huang, Yadong Zhang, Yinghui Xu +1
Dynamic convolution enhances model capacity by adaptively combining multiple kernels, yet faces critical trade-offs: prior works either (1) incur significant parameter overhead by…
DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer
Haiduo Huang, Jiangcheng Song, Yadong Zhang +1
Recent advances in knowledge distillation have emphasized the importance of decoupling different knowledge components. While existing methods utilize momentum mechanisms to separat…