Listen-to-Reason (L2R), an interpretable-by-design pipeline that passes audio to the LLM through an explicit, human-readable tree that outperforms all LALMs the authors compare against on SAKURA and trails them by 6-12 points on MMAU and MMAR, is proposed.
Pooneh Mousavi, M. Ravanelli, Cem Subakan· 0 citations
Large audio-language models (LALMs) are sensitive to input perturbations, such as noise, waveform corruption, and adversarial injections. We propose AnchorPrompt, an efficient adaptation method that keeps the model frozen and learns a single block of prompt vectors inserted at the decoder input, between the audio and q...
Pooneh Mousavi, Amir Ivry, M. Ravanelli et al.· 0 citations
Applying ALAS to four open-source Speech-LLMs across emotion recognition, open-ended SQA, and multi-choice audio understanding, it is found that the depth and strength of alignment reflect each model's audio-encoder design and the acoustic-versus-semantic demands of the task, and that ALAS tracks but does not duplicate...
Pooneh Mousavi, Yingzhi Wang, M. Ravanelli et al.· 4 citations
SPARE (Semantic Prediction for Audio REasoning), which introduces a register token aligned with the final conclusion using a cosine similarity loss with a Sentence-BERT embedding, conditions the model's latent space with the target semantic goal before reasoning begins.
Francesco Bonzi, Pooneh Mousavi, Cem Subakan et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.