{"total":106,"rows":[{"id":"2503.20215","title":"Qwen2.5-Omni Technical Report","created":"2025-03-26","cited_by_count":736,"area":"lr"},{"id":"2410.19168","title":"MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark","created":"2024-10-24","cited_by_count":288,"area":"lr"},{"id":"2408.16725","title":"Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming","created":"2024-08-29","cited_by_count":210,"area":"lr"},{"id":"2503.03983","title":"Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities","created":"2025-03-06","cited_by_count":133,"area":"lr"},{"id":"2505.17862","title":"Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalities","created":"2025-05-23","cited_by_count":110,"area":"lr"},{"id":"2506.04779","title":"MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark","created":"2025-06-05","cited_by_count":103,"area":"lr"},{"id":"2503.02318","title":"Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models","created":"2025-03-04","cited_by_count":95,"area":"lr"},{"id":"2404.11757","title":"Language Models Still Struggle to Zero-shot Reason about Time Series","created":"2024-04-17","cited_by_count":88,"area":"lr"},{"id":"2409.13682","title":"ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation","created":"2024-09-20","cited_by_count":67,"area":"lr"},{"id":"2408.15769","title":"A Survey on Evaluation of Multimodal Large Language Models","created":"2024-08-28","cited_by_count":46,"area":"lr"},{"id":"2505.13237","title":"SAKURA: On the Multi-hop Reasoning of Large Audio-Language Models Based on Speech and Audio Information","created":"2025-05-19","cited_by_count":42,"area":"lr"},{"id":"2402.01591","title":"BAT: Learning to Reason about Spatial Sounds with Large Language Models","created":"2024-02-02","cited_by_count":36,"area":"lr"},{"id":"2401.10446","title":"Large Language Models are Efficient Learners of Noise-Robust Speech Recognition","created":"2024-01-19","cited_by_count":31,"area":"lr"},{"id":"2406.19741","title":"ROS-LLM: A ROS framework for embodied AI with task feedback and structured reasoning","created":"2024-06-28","cited_by_count":27,"area":"lr"},{"id":"2507.15375","title":"STITCH: Simultaneous Thinking and Talking with Chunked Reasoning for Spoken Language Models","created":"2025-07-21","cited_by_count":26,"area":"lr"},{"id":"2512.12360","title":"VideoARM: Agentic Reasoning over Hierarchical Memory for Long-Form Video Understanding","created":"2025-12-13","cited_by_count":25,"area":"lr"},{"id":"2502.11775","title":"video-SALMONN-o1: Reasoning-enhanced Audio-visual Large Language Model","created":"2025-02-17","cited_by_count":24,"area":"lr"},{"id":"2510.06917","title":"SHANKS: Simultaneous Hearing and Thinking for Spoken Language Models","created":"2025-10-08","cited_by_count":19,"area":"lr"},{"id":"2506.05425","title":"SIV-Bench: A Video Benchmark for Social Interaction Understanding and Reasoning","created":"2025-06-05","cited_by_count":18,"area":"lr"},{"id":"2409.11538","title":"Chain-of-Thought Prompting for Speech Translation","created":"2024-09-17","cited_by_count":17,"area":"lr"},{"id":"2309.08859","title":"Rethinking Learning Rate Tuning in the Era of Large Language Models","created":"2023-09-16","cited_by_count":16,"area":"lr"},{"id":"2409.04927","title":"Just ASR + LLM? A Study on Speech Large Language Models' Ability to Identify and Understand Speaker in Spoken Dialogue","created":"2024-09-07","cited_by_count":16,"area":"lr"},{"id":"2312.17117","title":"Grounding-Prompter: Prompting LLM with Multimodal Information for Temporal Sentence Grounding in Long Videos","created":"2023-12-28","cited_by_count":14,"area":"lr"},{"id":"2505.24869","title":"SiLVR: A Simple Language-based Video Reasoning Framework","created":"2025-05-30","cited_by_count":14,"area":"lr"},{"id":"2510.05150","title":"Chronological Thinking in Full-Duplex Spoken Dialogue Language Models","created":"2025-10-02","cited_by_count":14,"area":"lr"},{"id":"2505.15000","title":"Towards Spoken Mathematical Reasoning: Benchmarking Speech-based Models over Multi-faceted Math Problems","created":"2025-05-21","cited_by_count":12,"area":"lr"},{"id":"2507.22886","title":"Towards Omnimodal Expressions and Reasoning in Referring Audio-Visual Segmentation","created":"2025-07-30","cited_by_count":11,"area":"lr"},{"id":"2601.16547","title":"CORD: Bridging the Audio-Text Reasoning Gap via Weighted On-policy Cross-modal Distillation","created":"2026-01-23","cited_by_count":11,"area":"lr"},{"id":"2306.07536","title":"TART: A plug-and-play Transformer module for task-agnostic reasoning","created":"2023-06-13","cited_by_count":10,"area":"lr"},{"id":"2505.13115","title":"Benchmarking and Confidence Evaluation of LALMs For Temporal Reasoning","created":"2025-05-19","cited_by_count":10,"area":"lr"},{"id":"2511.23478","title":"Video-R2: Reinforcing Consistent and Grounded Reasoning in Multimodal Language Models","created":"2025-11-28","cited_by_count":10,"area":"lr"},{"id":"2512.10359","title":"Tool-Augmented Spatiotemporal Reasoning for Streamlining Video Question Answering Task","created":"2025-12-11","cited_by_count":10,"area":"lr"},{"id":"2407.03169","title":"Investigating Decoder-only Large Language Models for Speech-to-text Translation","created":"2024-07-03","cited_by_count":9,"area":"lr"},{"id":"2509.21749","title":"Thinking with Sound: Audio Chain-of-Thought Enables Multimodal Reasoning in Large Audio-Language Models","created":"2025-09-26","cited_by_count":9,"area":"lr"},{"id":"2412.09818","title":"MERaLiON-AudioLLM: Bridging Audio and Language with Large Language Models","created":"2024-12-13","cited_by_count":8,"area":"lr"},{"id":"2505.23931","title":"Scaling up the think-aloud method","created":"2025-05-29","cited_by_count":8,"area":"lr"},{"id":"2506.01683","title":"Reasoning-Based Approach with Chain-of-Thought for Alzheimer's Detection Using Speech and Large Language Models","created":"2025-06-02","cited_by_count":8,"area":"lr"},{"id":"2510.23968","title":"Reasoning Visual Language Model for Chest X-Ray Analysis","created":"2025-10-28","cited_by_count":8,"area":"lr"},{"id":"2511.06606","title":"SPUR: A Plug-and-Play Framework for Integrating Spatial Audio Understanding and Reasoning into Large Audio-Language Models","created":"2025-11-10","cited_by_count":8,"area":"lr"},{"id":"2501.10937","title":"Leveraging Chain of Thought towards Empathetic Spoken Dialogue without Corresponding Question-Answering Data","created":"2025-01-19","cited_by_count":7,"area":"lr"},{"id":"2505.04147","title":"R^3-VQA: \"Read the Room\" by Video Social Reasoning","created":"2025-05-07","cited_by_count":6,"area":"lr"},{"id":"2505.12237","title":"From Shots to Stories: LLM-Assisted Video Editing with Unified Language Representations","created":"2025-05-18","cited_by_count":6,"area":"lr"},{"id":"2602.12135","title":"WavBench: Benchmarking Reasoning, Colloquialism, and Paralinguistics for End-to-End Spoken Dialogue Models","created":"2026-02-12","cited_by_count":6,"area":"lr"},{"id":"2602.13685","title":"AuTAgent: A Reinforcement Learning Framework for Tool-Augmented Audio Reasoning","created":"2026-02-14","cited_by_count":6,"area":"lr"},{"id":"2407.13505","title":"Robots Can Multitask Too: Integrating a Memory Architecture and LLMs for Enhanced Cross-Task Robot Action Generation","created":"2024-07-18","cited_by_count":5,"area":"lr"},{"id":"2502.18186","title":"Steering Language Model to Stable Speech Emotion Recognition via Contextual Perception and Chain of Thought","created":"2025-02-25","cited_by_count":5,"area":"lr"},{"id":"2505.07365","title":"Multi-Domain Audio Question Answering Benchmark Toward Acoustic Content Reasoning","created":"2025-05-12","cited_by_count":5,"area":"lr"},{"id":"2506.00722","title":"Chain-of-Thought Training for Open E2E Spoken Dialogue Systems","created":"2025-05-31","cited_by_count":5,"area":"lr"},{"id":"2506.23049","title":"AURA: Agent for Understanding, Reasoning, and Automated Tool Use in Voice-Driven Tasks","created":"2025-06-29","cited_by_count":5,"area":"lr"},{"id":"2510.02066","title":"Chain-of-Thought Reasoning in Streaming Full-Duplex End-to-End Spoken Dialogue Systems","created":"2025-10-02","cited_by_count":5,"area":"lr"},{"id":"2510.12185","title":"Not in Sync: Unveiling Temporal Bias in Audio Chat Models","created":"2025-10-14","cited_by_count":5,"area":"lr"},{"id":"2601.13742","title":"Hearing Between the Lines: Unlocking the Reasoning Power of LLMs for Speech Evaluation","created":"2026-01-20","cited_by_count":5,"area":"lr"},{"id":"2409.14526","title":"What Are They Doing? Joint Audio-Speech Co-Reasoning","created":"2024-09-22","cited_by_count":4,"area":"lr"},{"id":"2512.23881","title":"Breaking Audio Large Language Models by Attacking Only the Encoder: A Universal Targeted Latent-Space Audio Attack","created":"2025-12-29","cited_by_count":4,"area":"lr"},{"id":"2603.23607","title":"Reasoning models do not yet follow their reasoning in autonomous driving: The KITScenes LongTail Dataset","created":"2026-03-24","cited_by_count":4,"area":"lr"},{"id":"2605.08271","title":"Bridging Modalities, Spanning Time: Structured Memory for Ultra-Long Agentic Video Reasoning","created":"2026-05-08","cited_by_count":4,"area":"lr"},{"id":"2501.03624","title":"LLAMADRS: Evaluating Open-Source LLMs on Real Clinical Interviews--To Reason or Not to Reason?","created":"2025-01-07","cited_by_count":3,"area":"lr"},{"id":"2507.07306","title":"ViDove: A Translation Agent System with Multimodal Context and Memory-Augmented Reasoning","created":"2025-07-09","cited_by_count":3,"area":"lr"},{"id":"2510.11454","title":"Audio-Maestro: Enhancing Large Audio-Language Models with Tool-Augmented Reasoning","created":"2025-10-13","cited_by_count":3,"area":"lr"},{"id":"2511.21270","title":"Multi-Reward GRPO for Stable and Prosodic Single-Codebook TTS LLMs at Scale","created":"2025-11-26","cited_by_count":3,"area":"lr"},{"id":"2602.10439","title":"AudioRouter: Data Efficient Audio Understanding via RL based Dual Reasoning","created":"2026-02-11","cited_by_count":3,"area":"lr"},{"id":"2603.29616","title":"Video-Oasis: Rethinking Evaluation of Video Understanding","created":"2026-03-31","cited_by_count":3,"area":"lr"},{"id":"2409.17353","title":"Internalizing ASR with Implicit Chain of Thought for Efficient Speech-to-Speech Conversational LLM","created":"2024-09-25","cited_by_count":2,"area":"lr"},{"id":"2503.23395","title":"Scaling Auditory Cognition via Test-Time Compute in Audio Language Models","created":"2025-03-30","cited_by_count":1,"area":"lr"},{"id":"2509.14142","title":"MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook","created":"2025-09-17","cited_by_count":1,"area":"lr"},{"id":"2512.21706","title":"Enabling Conversational Behavior Reasoning Capabilities in Full-Duplex Speech","created":"2025-12-25","cited_by_count":1,"area":"lr"},{"id":"2603.09556","title":"ALARM: Audio-Language Alignment for Reasoning Models","created":"2026-03-10","cited_by_count":1,"area":"lr"},{"id":"2606.04474","title":"Entity Binding Failures in Speech LLM Reasoning: Diagnosis and Chain-of-Thought Intervention","created":"2026-06-03","cited_by_count":1,"area":"lr"},{"id":"2606.11260","title":"RAIL: Rethinking Auditory Intelligence in Large Audio-Language Models with a CHC-Grounded Benchmark","created":"2026-06-09","cited_by_count":1,"area":"lr"},{"id":"2606.15141","title":"EChO-Agent: Evidence Chain Orchestration Agent for Audio Reasoning","created":"2026-06-13","cited_by_count":1,"area":"lr"},{"id":"2608.03215","title":"GROW: Group-Relative Advantage-Weighted On-Policy Reinforcement Learning of Autoregressive-Diffusion Text-to-Speech model","created":"2026-08-04","cited_by_count":1,"area":"lr"},{"id":"2609.11864","title":"RetroThinker: Enabling Retrospective Thinking in Speech LLMs","created":"2026-09-10","cited_by_count":1,"area":"lr"},{"id":"2609.20849","title":"Enhancing Audio Reasoning via Semantic Summary Prediction","created":"2026-08-07","cited_by_count":1,"area":"lr"},{"id":"2609.31193","title":"Who Says What: Symbolic Trimodal Binding Mechanisms in Audio-Visual LLMs","created":"2026-09-25","cited_by_count":1,"area":"lr"},{"id":"2407.21054","title":"Sentiment Reasoning for Healthcare","created":"2024-07-24","cited_by_count":0,"area":"lr"},{"id":"2506.11558","title":"DaMO: A Data-Efficient Multimodal Orchestrator for Temporal Reasoning with Video LLMs","created":"2025-06-13","cited_by_count":0,"area":"lr"},{"id":"2506.13300","title":"Seewo's Submission to MLC-SLM: Lessons learned from Speech Reasoning Language Models","created":"2025-06-16","cited_by_count":0,"area":"lr"},{"id":"2507.01544","title":"MARVIS: Modality Adaptive Reasoning over VISualizations","created":"2025-07-02","cited_by_count":0,"area":"lr"},{"id":"2509.22014","title":"Lightweight Structured Multimodal Reasoning for Clinical Scene Understanding in Robotics","created":"2025-09-26","cited_by_count":0,"area":"lr"},{"id":"2511.15578","title":"AVATAAR: Agentic Video Answering via Temporal Adaptive Alignment and Reasoning","created":"2025-11-19","cited_by_count":0,"area":"lr"},{"id":"2512.02743","title":"Reasoning-Aware Multimodal Fusion for Hateful Video Detection","created":"2025-12-02","cited_by_count":0,"area":"lr"},{"id":"2601.22889","title":"DiffuSpeech: Silent Thought, Spoken Answer via Unified Speech-Text Diffusion","created":"2026-01-30","cited_by_count":0,"area":"lr"},{"id":"2602.08996","title":"Generalizing Sports Feedback Generation by Watching Competitions and Reading Books: A Rock Climbing Case Study","created":"2026-02-09","cited_by_count":0,"area":"lr"},{"id":"2603.13374","title":"Geometry-Aware Semantic Reasoning for Training Free Video Anomaly Detection","created":"2026-03-10","cited_by_count":0,"area":"lr"},{"id":"2603.17822","title":"Multi-Source Evidence Fusion for Audio Question Answering","created":"2026-03-18","cited_by_count":0,"area":"lr"},{"id":"2604.20319","title":"SurgCoT: Advancing Spatiotemporal Reasoning in Surgical Videos through a Chain-of-Thought Benchmark","created":"2026-04-22","cited_by_count":0,"area":"lr"},{"id":"2605.08186","title":"Rethinking Entropy Minimization in Test-Time Adaptation for Autoregressive Models","created":"2026-05-05","cited_by_count":0,"area":"lr"},{"id":"2605.12987","title":"Leveraging Multimodal Self-Consistency Reasoning in Coding Motivational Interviewing for Alcohol Use Reduction","created":"2026-05-13","cited_by_count":0,"area":"lr"},{"id":"2606.08425","title":"TinyGiantALM: A Compact Audio-Language Model for Intent-Aware Reasoning under Resource Constraints","created":"2026-06-07","cited_by_count":0,"area":"lr"},{"id":"2606.12199","title":"Which Speech Representation Better Matches Text-Native Reasoning? A Study of Speech-Text Alignment on Frame Rate and Representation","created":"2026-06-10","cited_by_count":0,"area":"lr"},{"id":"2606.12902","title":"PRISM: Prosody-Integrated Multi-Agent Reasoning Framework for Empathetic Spoken Dialogue","created":"2026-06-11","cited_by_count":0,"area":"lr"},{"id":"2606.25552","title":"SFL-MTSC: Leveraging Semantic Frame-Level Multi-Task Self-Consistency for Robust Multi-Intent Spoken Language Understanding","created":"2026-06-24","cited_by_count":0,"area":"lr"},{"id":"2607.02757","title":"Reinforcement Learning for Data-Efficient Code-Switched ASR","created":"2026-07-02","cited_by_count":0,"area":"lr"},{"id":"2607.10092","title":"Efficiently Adapting Spoken Language Models for the Singaporean Context","created":"2026-07-11","cited_by_count":0,"area":"lr"},{"id":"2608.03161","title":"Evidence-Grounded Multimodal Knowledge Graph Construction for Multi-Lecture Educational Reasoning","created":"2026-08-04","cited_by_count":0,"area":"lr"},{"id":"2608.16539","title":"Listen, Reason, and Segment: Aligning LALMs with Editorial Judgment for Media Chapterization","created":"2026-08-17","cited_by_count":0,"area":"lr"},{"id":"2608.25177","title":"AudioLens: Multi-Perspective Speech Clustering with Reasoning Audio-Language Models","created":"2026-08-25","cited_by_count":0,"area":"lr"},{"id":"2608.27176","title":"When Text Misleads: Inconsistent-Aware Reasoning for Audio-Grounded Dialogue","created":"2026-08-27","cited_by_count":0,"area":"lr"},{"id":"2608.29120","title":"HEAR Who Said What: Unlocking Speaker-Attributed Reasoning via Counterfactual Voice Grounding","created":"2026-08-29","cited_by_count":0,"area":"lr"},{"id":"2609.21663","title":"Rethinking Human-Aligned Evaluation: An Analysis of Semantic Metrics Beyond WER","created":"2026-09-18","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}