Transformer-based models have significantly advanced image captioning through self-attention mechanisms and parallel computation. However, existing methods typically adopt teacher-forcing strategies during training by conditioning the decoder exclusively on ground-truth tokens, whereas at inference, captions are genera...
Yuchen Ren, Xin Chen, Hong-Rui Yuan et al.· IEEE Transactions on Image P...· 0 citations
This work presents SemPIC, which trains a LoRA-enabled Writer to compile native per-layer document KVs through behavioral distillation while retaining the pretrained decoder as an unchanged Reader, and introduces KV Gradient Checkpointing, which reduces peak training memory without severing gradients through cached KVs...
Hui Xie, Peng Xiao, Yutong Deng et al.· arXiv.org· 0 citations
PTQ4SNN is proposed, a membrane-aware post-training quantization framework that jointly quantizes weights and recurrent membrane states using only a small calibration set and effectively preserves model accuracy under W4 quantization and approximately 4-bit membrane precision.
Hui Xie, Tong Shi, Haotong Qin et al.· 0 citations
Hardware-agnostic strategies for accelerating text-to-image diffusion, such as timestep distillation and feature caching, can reduce inference time without custom kernels or system-level optimization. Among them, multi-resolution generation strategies have recently received broad attention, attaining more than 5x speed...
Xingyu Zheng, Xianglong Liu, Yifu Ding et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
