Search papers, labs, and topics across Lattice.
3
0
6
3
NAPE achieves state-of-the-art performance in audio representation learning by simplifying the pre-training process to a single autoregressive prediction task.
TCR transforms LLM preference alignment by focusing on the reasoning process, leading to substantial improvements in model performance across diverse benchmarks.
LALMs struggle with polyphonic audio, losing significant performance on tasks requiring reasoning about concurrent sound events, as revealed by the new PolyBench benchmark.
