TWNM framework equips audio-language models with spatial scene analysis via FOA simulation and metadata-grounded training, reaching 70.8% accuracy on a new ASA benchmark.
Air-bench: Benchmarking large audio-language models via generative comprehension
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
VoiceBench is the first benchmark for multi-faceted evaluation of LLM voice assistants using real and synthetic spoken instructions with speaker, environmental, and content variations.
LIME reduces hallucinations in multimodal LLMs by using LRP to boost perceptual modality contributions through inference-time KV updates.
DuplexSLA is a dual-stream three-channel full-duplex model that synchronizes continuous user audio, discrete assistant audio, and rate-limited action text for native turn-taking and in-conversation tool calling.
citing papers explorer
-
The World is Not Mono: Enabling Spatial Understanding in Large Audio-Language Models
TWNM framework equips audio-language models with spatial scene analysis via FOA simulation and metadata-grounded training, reaching 70.8% accuracy on a new ASA benchmark.
-
VoiceBench: Benchmarking LLM-Based Voice Assistants
VoiceBench is the first benchmark for multi-faceted evaluation of LLM voice assistants using real and synthetic spoken instructions with speaker, environmental, and content variations.
-
Mitigating Multimodal LLMs Hallucinations via Relevance Propagation at Inference Time
LIME reduces hallucinations in multimodal LLMs by using LRP to boost perceptual modality contributions through inference-time KV updates.
-
DuplexSLA: A Full-Duplex Spoken Language Model with Synchronized Speech, Language, and Action
DuplexSLA is a dual-stream three-channel full-duplex model that synchronizes continuous user audio, discrete assistant audio, and rate-limited action text for native turn-taking and in-conversation tool calling.