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

arXiv:2610.01560 · cs.CL, cs.LG, cs.SD · Submitted 2026-10-01 · Read on arXiv

cs.CL, cs.LG, cs.SD

Submitted: 2026-10-01

Updated: 2026-10-01

Terminology

• Accuracy — 35× in this paper · explained in 1 episode
• Latent Reasoning — 30× in this paper · explained in 2 episodes
• Trace — 27× in this paper · explained in 2 episodes
• Benchmark — 22× in this paper · explained in 2 episodes
• Embeddings — 10× in this paper · explained in 2 episodes
• GRPO — 5× in this paper · explained in 6 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Latent Space — 4× in this paper · explained in 7 episodes
• Reinforcement Learning — 4× in this paper · explained in 4 episodes
• Transformer — 4× in this paper · explained in 2 episodes
• Abstraction — 3× in this paper · explained in 1 episode
• Alignment — 3× in this paper · explained in 1 episode
• Core — 3× in this paper · explained in 2 episodes
• Large Language Model — 3× in this paper
• Verification — 3× in this paper · explained in 2 episodes
• Adaptive Reasoning — 2× in this paper · explained in 2 episodes
• Decode — 2× in this paper · explained in 2 episodes
• Distillation — 2× in this paper · explained in 2 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• Reasoning Traces — 2× in this paper · explained in 3 episodes
• Self-distillation — 2× in this paper · explained in 6 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Affective Computing — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Aperture — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Data Augmentation — 1× in this paper · explained in 7 episodes
• Exposure Bias — 1× in this paper · explained in 2 episodes
• Gaussian Mixture Model (GMM) — 1× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Scaffolding — 1× in this paper · explained in 3 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Playing a Part: Speaker Verification at the Movies
• The MSP-Podcast Corpus
• GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio
• Compressed Chain of Thought: Efficient Reasoning Through Dense Representations
• Training Verifiers to Solve Math Word Problems
• LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning
• LLM Latent Reasoning as Chain of Superposition
• Latent-GRPO: Group Relative Policy Optimization for Latent Reasoning
• Continuous Audio Thinking for Large Audio Language Models
• Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning
• Measuring Mathematical Problem Solving With the MATH Dataset
• Qwen3-TTS Technical Report
• Kimi-Audio Technical Report
• Tulu 3: Pushing Frontiers in Open Language Model Post-Training
• EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis
• EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• EmotionTalk: An Interactive Chinese Multimodal Emotion Dataset With Rich Annotations
• Step-Audio-R1 Technical Report
• Marco-Voice Technical Report

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering