ORCA splits Q-Former queries into orthogonally constrained groups, reversing directional collapse and speaker-indistinguishability in audio-LLM connectors and gaining 26.4 points on SAKURA multi-hop reasoning.
Anatomy of the modality gap: Dissecting the internal states of end-to-end speech llms,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Layer-wise pooling plus RIR-augmented synthetic speech matches a 100%-real ASR baseline with only 25% real data (13.6 h) and beats it at higher real fractions.
citing papers explorer
-
Escaping the Procrustean Bed: Groupwise Orthogonal Connectors for Audio-Language Models
ORCA splits Q-Former queries into orthogonally constrained groups, reversing directional collapse and speaker-indistinguishability in audio-LLM connectors and gaining 26.4 points on SAKURA multi-hop reasoning.
-
How to Leverage Synthetic Speech for LLM-Based ASR Systems?
Layer-wise pooling plus RIR-augmented synthetic speech matches a 100%-real ASR baseline with only 25% real data (13.6 h) and beats it at higher real fractions.