Related papers: AudioRouter: Data Efficient Audio Understanding vi…

Large audio-language models (LALMs) have achieved near-human performance in sentence-level transcription and emotion recognition. However, existing evaluations focus mainly on surface-level perception, leaving the capacity of models for…

Perceiving and understanding non-speech sounds and non-verbal speech is essential to making decisions that help us interact with our surroundings. In this paper, we propose GAMA, a novel General-purpose Large Audio-Language Model (LALM)…

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…

Large Audio Language Models (LALM) combine the audio perception models and the Large Language Models (LLM) and show a remarkable ability to reason about the input audio, infer the meaning, and understand the intent. However, these systems…

Reinforcement learning (RL) has demonstrated potential in enhancing the reasoning capabilities of large language models (LLMs), but such training typically demands substantial efforts in creating and annotating data. In this work, we…

While Large Audio Language Models (LALMs) achieve strong performance on short audio, they degrade on long-form inputs. This degradation is more severe in temporal awareness tasks, where temporal alignment becomes increasingly inaccurate as…

Recent work explores latent reasoning to improve reasoning efficiency by replacing explicit reasoning trajectories with continuous representations in a latent space, yet its effectiveness varies across settings. Analysis of model confidence…

Small Language Models (SLMs) are a cost-effective alternative to Large Language Models (LLMs), but often struggle with complex reasoning due to their limited capacity and a tendency to produce mistakes or inconsistent answers during…

Large language models (LLMs) exhibit impressive capabilities across a wide range of tasks, yet the choice of which model to use often involves a trade-off between performance and cost. More powerful models, though effective, come with…

Large Language Models (LLMs), when enhanced through reasoning-oriented post-training, evolve into powerful Large Reasoning Models (LRMs). Tool-Integrated Reasoning (TIR) further extends their capabilities by incorporating external tools,…

We present a novel podcast recommender system deployed at industrial scale. This system successfully optimizes personal listening journeys that unfold over months for hundreds of millions of listeners. In deviating from the pervasive…

Large language models (LLMs) have demonstrated exceptional performance across a wide range of natural language tasks. However, selecting the optimal LLM to respond to a user query often necessitates a delicate balance between performance…

Understanding and reasoning over non-speech sounds and music are crucial for both humans and AI agents to interact effectively with their environments. In this paper, we introduce Audio Flamingo 2 (AF2), an Audio-Language Model (ALM) with…

Recent advancements in large audio-language models (LALMs) have shown impressive capabilities in understanding and reasoning about audio and speech information. However, these models still face challenges, including hallucinating…

While reasoning-augmented large language models (RLLMs) significantly enhance complex task performance through extended reasoning chains, they inevitably introduce substantial unnecessary token consumption, particularly for simpler problems…

Large Audio Language Models (LALMs) represent an important frontier in multimodal AI, addressing diverse audio tasks. Recently, post-training of LALMs has received increasing attention due to significant performance improvements over…

Recent work shows that reinforcement learning(RL) can markedly sharpen the reasoning ability of large language models (LLMs) by prompting them to "think before answering." Yet whether and how these gains transfer to audio-language reasoning…

Explainable Reinforcement Learning (XRL) has emerged as a promising approach in improving the transparency of Reinforcement Learning (RL) agents. However, there remains a gap between complex RL policies and domain experts, due to the…

Current speech evaluation suffers from two critical limitations: the need and difficulty of designing specialized systems targeting individual audio characteristics, and poor correlation between automatic evaluation methods and human…

Large audio-language models (LALMs) extend the large language models with multimodal understanding in speech, audio, etc. While their performances on speech and audio-processing tasks are extensively studied, their reasoning abilities…