arXiv Machine Learning October 7, 2026 By Lee Seung-woo, Bowen Qi

AdaLoop: Adaptive-Depth Latent Reasoning for Audio Language Models

Read the original on arXiv Machine Learning →

AdaLoop is a lightweight recurrent module that adaptively determines how many latent refinement steps are needed for audio–question pairs, allowing deeper reasoning only when necessary. It shares a transformer block that iterates over the audio representation guided by the question, with a learned halting mechanism that exits the loop once the representation is ready. Adding fewer than 3 % of the base model’s parameters, AdaLoop improves average accuracy by 2.9 to 3.8 points across three distinct models, especially on perception-heavy subtasks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

llms

arXiv AI

Sep 30

Thinking in Depth, Speaking Directly: Recurrent Latent Reasoning for Paralinguistically Grounded Spoken Dialogue

arXiv:2609.37818v1 Announce Type: cross Abstract: Empathetic spoken dialogue requires models to use both what is said and how it is said to decide how to respond. Explicit CoT can improve paralinguis...

By Shengbo Cai, Yuxiang Wang, Jingran Xie, Zhisheng Zhang, Shun Lei, Di Cao, Teddy Sun, Zhiyong Wu

llms fine-tuning efficiency benchmarks

arXiv AI

Sep 10

Audio-Maestro: Enhancing Large Audio-Language Models with Tool-Augmented Reasoning

arXiv:2510.11454v2 Announce Type: replace-cross Abstract: Recent advancements in large multimodal models (LMMs) have shown strong capabilities in audio understanding. However, most systems rely solel...

By Kuan-Yi Lee, Tsung-En Lin, Hung-Yi Lee

llms multimodal safety

arXiv Computation and Language

Sep 21

Enhancing Audio Reasoning via Semantic Summary Prediction

arXiv:2609.20849v1 Announce Type: new Abstract: Large Audio Language Models (LALMs) perform well on complex question answering but often show a reasoning gap, where explicit Chain-of-Thought (CoT) re...

By Francesco Bonzi, Pooneh Mousavi, Cem Subakan, Mirco Ravanelli

llms rag diffusion nlp

arXiv AI

Jun 15

AudioDER: A Deduplication-Enhanced Reasoning Dataset for Post-Training Large Audio-Language Models

arXiv:2606. 14591v1 Announce Type: cross Abstract: Large Audio-Language Models (LALMs) have shown strong performance on a wide range of audio understanding tasks, yet they still struggle with complex audio reasoning.

By Hui Geng, Yi Su, Han Yin, Tianjiao Wan, Qisheng Xu, Jiaxin Chen, Zijian Gao, Hengzhu Liu, Xie Chen, Kele Xu

llms benchmarks

arXiv Machine Learning

5d ago

AURAL: Adaptive Latent Reasoning with Joint Chunk for Speech Language Models

AURAL is a speech language model that performs adaptive latent reasoning by modeling multiple plausible reasoning continuations in latent space and jointly predicting chunks of future states, thereby reducing sequential forward passes and latency. The authors introduce a large bilingual dataset, AuralReason-683K, containing concise chain‑of‑thought annotations for emotion recognition, empathetic dialogue, and general reasoning, and use reinforcement learning (AURAL‑RL) to reward concise, high‑quality reasoning that adapts to problem difficulty. Experiments on two backbones show that AURAL‑RL matches or exceeds chain‑of‑thought reinforcement learning while achieving significant latency reductions, such as an 11.8× speed‑up on Qwen2.5‑Omni. "whyItMatters":"The work demonstrates that latent reasoning can match the performance of explicit chain‑of‑thought methods while dramatically cutting response time, addressing the trade‑off between intelligence and speed in speech language models."

By Yuxiang Wang, Kunyu Feng, Yuancheng Wang, Zihang Liu, Shengbo Cai, Qinke Ni, Wan Lin, Tao Feng, Yingda shen, Ming-Hao Hsu, Zhixian Zhao, Liqiang Zhang, Teddy Sun, Steve Yves, Zhizheng Wu

llms diffusion reinforcement-learning

arXiv Machine Learning

Jun 18

Investigating Faithfulness in Large Audio Language Models

arXiv:2509. 22363v4 Announce Type: replace Abstract: Large Audio Language Models (LALMs) integrate audio encoders with pretrained Large Language Models to perform complex multimodal reasoning tasks.

By Pooneh Mousavi, Lovenya Jain, Mirco Ravanelli, Cem Subakan

llms multimodal benchmarks safety

One email a morning, machine-written

Related stories

Thinking in Depth, Speaking Directly: Recurrent Latent Reasoning for Paralinguistically Grounded Spoken Dialogue

Audio-Maestro: Enhancing Large Audio-Language Models with Tool-Augmented Reasoning

Enhancing Audio Reasoning via Semantic Summary Prediction

AudioDER: A Deduplication-Enhanced Reasoning Dataset for Post-Training Large Audio-Language Models

AURAL: Adaptive Latent Reasoning with Joint Chunk for Speech Language Models

Investigating Faithfulness in Large Audio Language Models