4 accepted papers
This work studies how to adaptively recompute key–value (KV) caches for diffusion large language models (DLMs) to maximize prediction accuracy while minimizing decoding latency. Prior methods' decoders recompute QKV for all tokens at every denoising step and layer, despite KV states changing little…
Pruning at Initialization (PaI) is a technique in neural network optimization characterized by the proactive elimination of weights before the network's training on designated tasks. This innovative strategy potentially reduces the costs for training and inference, significantly advancing computatio…
Non-autoregressive transformers (NATs) predict entire sequences in parallel to reduce decoding latency, but they often encounter performance challenges due to the multi-modality problem. A recent advancement, the Directed Acyclic Transformer (DAT), addresses this issue by capturing multiple translat…
Few-shot image classification remains challenging due to the scarcity of labeled training examples. Augmenting them with synthetic data has emerged as a promising way to alleviate this issue, but models trained on synthetic samples often face performance degradation due to the inherent gap between r…