Today's trail

Large audio-language models (LALMs) understand music, yet struggle to locate a described moment in time. We ask whether this reflects missing temporal information or a bottleneck in how the time span is extracted. Using a paired-query probe built from Slakh2100 stem…

Masked diffusion language models have emerged as an alternative to autoregressive models, enabling parallel token generation. However, standard masked diffusion language models use a shared noise schedule across positions without explicitly encoding which positions should be…

People share and understand others' experiences differently based on their social identities; often, people empathize more when the other person belongs to their ingroup compared to an outgroup. While this intergroup empathy gap is well-studied in social psychology, it remains…

Federated learning (FL) keeps data at its source, but locality alone does not make a federation trustworthy. Without sufficient observability, an aggregator cannot determine whether the client service was healthy, the local data pipeline was trustworthy, or contractual…