ReSpike: Residual Frames-based Hybrid Spiking Neural Networks for Efficient Action Recognitionby Shiting Xiao, Yuhang Li,…
Spatially-Aware Diffusion Models with Cross-Attention for Global Field Reconstruction with Sparse Observationsby Yilin Zhuang, Sibo…
SALSA: Speedy ASR-LLM Synchronous Aggregationby Ashish Mittal, Darshan Prabhu, Sunita Sarawagi, Preethi JyothiFirst submitted to…
CrisperWhisper: Accurate Timestamps on Verbatim Speech Transcriptionsby Laurin Wagner, Bernhard Thallinger, Mario ZusagFirst submitted to…
Enhancing Conditional Image Generation with Explainable Latent Space Manipulationby Kshitij PathaniaFirst submitted to arxiv on:…