GitHub

vLLM BART Model Plugin

BART is an encoder-decoder model that is particularly effective for sequence-to-sequence tasks like summarization, translation, and text generation. Florence-2 is a vision-language model from ...
GitHub

zipformer示例模型encoder-epoch-99-avg-1.onnx转换rknn报错

W load_onnx: The config.mean_values is None, zeros will be set for input 0! W load_onnx: The config.std_values is None, ones will be set for input 0! 2026-01-29 16:01:31.988240739 [E:onnxruntime:, ...
IEEE

Transformer Encoder-Based Sequence Modeling for Effective Video Summarization

Abstract: Creating concise and preceptive video summaries has become more important due to the rapid expansion of digital video content. Long-range temporal dependencies are difficult for traditional ...
IEEE

Adaptive Cyclic Learning Rate for Long-Term Time-Series Forecasting on Encoder-Decoder and Encoder-Only Deep Learning Model Architectures

Abstract: Long-term time-series forecasting remains a critical challenge, with deep learning models often facing persistent training instability. This study reveals a critical insight: the ...