3 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
LoopSLM builds on looped Transformers for latent reasoning, reusing a decoder block to refine hidden states with acoustic grounding at every pass, and further narrows the perception-reasoning gap by separating learning to reason from learning to respond, enabling direct inference without CoT.
Large Audio Language Models (LALMs) utilize either continuous features or discrete tokens, yet the optimal representation paradigm for general audio understanding remains debated. Existing benchmarks often focus on narrow domains or evaluate encoders outside LALM contexts. To address these gaps, we systematically evalu...
A Semantic Bottleneck that compresses 1280-dimensional semantic encoder features into 128 dimensions, regularized by the proposed time-relation loss for temporal feature consistency is introduced and a dual-level semantic supervision method is designed that leverages both high- and low-dimensional semantic signals, ena...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
