Search papers, labs, and topics across Lattice.
5
0
7
5
A single universal speech enhancement model can effectively adapt to multiple latency requirements without sacrificing performance, challenging the need for specialized models.
A CNN can find hundreds of new gravitational lens candidates in Euclid data, even with limited training data and compute.
Bitstream-corrupted video restoration remains a significant challenge, even with recent advances, as revealed by the NTIRE 2026 challenge results.
Text-only LLMs already contain surprisingly diverse levels of auditory knowledge, and this pre-existing knowledge strongly predicts their performance when adapted for audio-language tasks.
Time-shifted anechoic speech beats early reflections as a training target for universal speech enhancement, leading to better perceptual quality and ASR performance.
