Related papers: Task-Aware Answer Preservation under Audio Compres…
While multi-audio understanding is critical for large audio-language models (LALMs), it remains underexplored. We introduce MUGEN, a comprehensive benchmark evaluating this capability across speech, general audio, and music. Our experiments…
Despite the strong performance of large audio language models (LALMs) in various tasks, exactly how and where they integrate acoustic features with textual context remains unclear. We adapt causal tracing to investigate the internal…
Retrieval-augmented generation (RAG) often suffers from long and noisy retrieved contexts. Prior context compression methods rely on predefined importance metrics or supervised compression models, rather than on the model's own…
Retrieval-augmented generation improves the factual accuracy of Large Language Models (LLMs) by incorporating external context, but often suffers from irrelevant retrieved content that hinders effectiveness. Context compression addresses…
Large language models (LLMs) are increasingly deployed in multi-turn dialogue settings, yet their behavior remains bottlenecked by naive history management strategies. Replaying the full conversation at every turn is simple but costly,…
Matrix-level low-rank compression is a promising way to reduce the cost of large language models, but running compression and evaluating the resulting models on language tasks can be prohibitively expensive. Can compression-induced…
Low-rank and sparse composite approximation is a natural idea to compress Large Language Models (LLMs). However, such an idea faces two primary challenges that adversely affect the performance of existing methods. The first challenge…
Large language models (LLMs) have shown exceptional versatility in natural language processing, prompting recent efforts to extend their multimodal capabilities to speech processing through the development of audio large language models…
Conversational systems relying on text-based large language models (LLMs) often overlook paralinguistic cues, essential for understanding emotions and intentions. Speech-language models (SLMs), which use speech as input, are emerging as a…
Large Language Models (LLMs) have demonstrated impressive performance on multiple-choice question answering (MCQA) benchmarks, yet they remain highly vulnerable to minor input perturbations. In this paper, we introduce and evaluate Token…
Safety-aligned large language models (LLMs) often generate refusal responses to harmless queries due to the over-refusal problem. However, existing methods for mitigating over-refusal cannot maintain a low refusal ratio for harmless queries…
Multimodal large language models (MLLMs) have recently demonstrated strong capabilities in understanding and generating responses from diverse visual inputs, including high-resolution images and long video sequences. As these models scale…
The rapid advancement of Large Language Models (LLMs) has spurred significant progress in Large Speech-Language Models (LSLMs), enhancing their capabilities in both speech understanding and generation. While existing LSLMs often concentrate…
Large Language Models (LLMs) face limitations due to the high demand on GPU memory and computational resources when handling long contexts. While sparsify the Key-Value (KV) cache of transformer model is a typical strategy to alleviate…
Large language models face challenges in long-context question answering, where key evidence of a query may be dispersed across millions of tokens. Existing works equip large language models with a memory buffer that is dynamically updated…
While Contrastive Decoding (CD) has proven effective at enhancing Large Audio Language Models (LALMs), the underlying mechanisms driving its success and the comparative efficacy of different strategies remain unclear. This study…
Although text-to-audio generation has made remarkable progress in realism and diversity, the development of evaluation metrics has not kept pace. Widely-adopted approaches, typically based on embedding similarity like CLAPScore, effectively…
Omnimodal large language models (Omni-LLMs) show strong capability in audio-video understanding, but their practical deployment remains limited by high inference cost of long video streams and dense audio sequences. Despite recent progress,…
Auscultation is a vital diagnostic tool, yet its utility is often limited by subjective interpretation. While general-purpose Audio-Language Models (ALMs) excel in general domains, they struggle with the nuances of physiological signals. We…
This paper presents the Interspeech 2026 Audio Encoder Capability Challenge, a benchmark specifically designed to evaluate and advance the performance of pre-trained audio encoders as front-end modules for Large Audio Language Models…