{"total":102,"rows":[{"id":"2510.10689","title":"OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs","created":"2025-10-12","cited_by_count":59,"area":"lr"},{"id":"2511.15848","title":"Step-Audio-R1 Technical Report","created":"2025-11-19","cited_by_count":36,"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":"2512.12772","title":"JointAVBench: A Benchmark for Joint Audio-Visual Reasoning Evaluation","created":"2025-12-14","cited_by_count":17,"area":"lr"},{"id":"2603.14145","title":"MMOU: A Massive Multi-Task Omni Understanding and Reasoning Benchmark for Long and Complex Real-World Videos","created":"2026-03-14","cited_by_count":14,"area":"lr"},{"id":"2601.03467","title":"ThinkRL-Edit: Thinking in Reinforcement Learning for Reasoning-Centric Image Editing","created":"2026-01-06","cited_by_count":12,"area":"lr"},{"id":"2603.12746","title":"Thinking in Dynamics: How Multimodal Large Language Models Perceive, Track, and Reason Dynamics in Physical 4D World","created":"2026-03-13","cited_by_count":12,"area":"lr"},{"id":"2602.05847","title":"OmniVideo-R1: Reinforcing Audio-visual Reasoning with Query Intention and Modality Attention","created":"2026-02-05","cited_by_count":11,"area":"lr"},{"id":"2601.05543","title":"Closing the Modality Reasoning Gap for Speech Large Language Models","created":"2026-01-09","cited_by_count":9,"area":"lr"},{"id":"2509.24210","title":"BeyondBench: Contamination-Resistant Evaluation of Reasoning in Language Models","created":"2025-09-29","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":"2512.06373","title":"VG-Refiner: Towards Tool-Refined Referring Grounded Reasoning via Agentic Reinforcement Learning","created":"2025-12-06","cited_by_count":8,"area":"lr"},{"id":"2604.24401","title":"All That Glitters Is Not Audio: Rethinking Text Priors and Audio Reliance in Audio-Language Evaluation","created":"2026-04-27","cited_by_count":8,"area":"lr"},{"id":"2606.14702","title":"OmniVideo-100K: A Dataset for Audio-Visual Reasoning through Structured Scripts and Evidence Chains","created":"2026-06-12","cited_by_count":8,"area":"lr"},{"id":"2512.10931","title":"Asynchronous Reasoning: Training-Free Interactive Thinking LLMs","created":"2025-12-11","cited_by_count":7,"area":"lr"},{"id":"2602.06166","title":"M3: High-fidelity Text-to-Image Generation via Multi-Modal, Multi-Agent and Multi-Round Visual Reasoning","created":"2026-02-05","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":"2602.14224","title":"The Interspeech 2026 Audio Reasoning Challenge: Evaluating Reasoning Process Quality for Audio Reasoning Models and Agents","created":"2026-02-15","cited_by_count":6,"area":"lr"},{"id":"2603.14337","title":"On the Nature of Attention Sink that Shapes Decoding Strategy in Omni-LLMs","created":"2026-03-15","cited_by_count":6,"area":"lr"},{"id":"2512.03783","title":"Omni-AutoThink: Adaptive Multimodal Reasoning via Reinforcement Learning","created":"2025-12-03","cited_by_count":5,"area":"lr"},{"id":"2512.07558","title":"ReLaX: Reasoning with Latent Exploration for Large Reasoning Models","created":"2025-12-08","cited_by_count":5,"area":"lr"},{"id":"2512.12756","title":"FysicsWorld: A Unified Full-Modality Benchmark for Any-to-Any Understanding, Generation, and Reasoning","created":"2025-12-14","cited_by_count":5,"area":"lr"},{"id":"2512.16978","title":"A Benchmark for Omni-Modal Reasoning in Long Videos","created":"2025-12-18","cited_by_count":5,"area":"lr"},{"id":"2601.17645","title":"AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking","created":"2026-01-25","cited_by_count":5,"area":"lr"},{"id":"2605.03314","title":"When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning","created":"2026-05-05","cited_by_count":5,"area":"lr"},{"id":"2510.19358","title":"M3-SLU: Evaluating Speaker-Attributed Reasoning in Multimodal Large Language Models","created":"2025-10-22","cited_by_count":4,"area":"lr"},{"id":"2602.18527","title":"JAEGER: Joint 3D Audio-Visual Grounding and Reasoning in Simulated Physical Environments","created":"2026-02-20","cited_by_count":4,"area":"lr"},{"id":"2606.07433","title":"Watch, Remember, Reason: Human-View Video Understanding with MLLMs","created":"2026-06-05","cited_by_count":4,"area":"lr"},{"id":"2605.27741","title":"Escape the Language Prior: Mitigating Late-Stage Modality Collapse in Audio Reasoning via Modality-Aware Policy Optimization","created":"2026-05-26","cited_by_count":3,"area":"lr"},{"id":"2605.28192","title":"Agentic Active Omni-Modal Perception for Multi-Hop Audio-Visual Reasoning","created":"2026-05-27","cited_by_count":3,"area":"lr"},{"id":"2606.25325","title":"Omni-Perception Policy Optimization for Multimodal Emotion Reasoning","created":"2026-06-24","cited_by_count":3,"area":"lr"},{"id":"2607.19339","title":"OmniReasoner: Thinking with Long Audio-Video via Native Tool Use","created":"2026-07-21","cited_by_count":3,"area":"lr"},{"id":"2607.20166","title":"Audio-Zero: Label-Free Self-Evolution for Fine-Grained Audio Reasoning","created":"2026-07-22","cited_by_count":3,"area":"lr"},{"id":"2607.21550","title":"X$^3$-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment","created":"2026-07-23","cited_by_count":3,"area":"lr"},{"id":"2601.08748","title":"UR-Bench: A Benchmark for Multi-Hop Reasoning over Ultra-High-Resolution Images","created":"2025-12-31","cited_by_count":2,"area":"lr"},{"id":"2601.16538","title":"OnlineSI: Taming Large Language Model for Online 3D Understanding and Grounding","created":"2026-01-23","cited_by_count":2,"area":"lr"},{"id":"2602.11509","title":"Multimodal Fact-Level Attribution for Verifiable Reasoning","created":"2026-02-12","cited_by_count":2,"area":"lr"},{"id":"2604.00610","title":"Speech LLMs are Contextual Reasoning Transcribers","created":"2026-04-01","cited_by_count":2,"area":"lr"},{"id":"2605.09906","title":"Separate First, Fuse Later: Mitigating Cross-Modal Interference in Audio-Visual LLMs Reasoning with Modality-Specific Chain-of-Thought","created":"2026-05-11","cited_by_count":2,"area":"lr"},{"id":"2605.15044","title":"SpeakerLLM: A Speaker-Specialized Audio-LLM for Speaker Understanding and Verification Reasoning","created":"2026-05-14","cited_by_count":2,"area":"lr"},{"id":"2605.27190","title":"Learning When to Think While Listening in Large Audio-Language Models","created":"2026-05-26","cited_by_count":2,"area":"lr"},{"id":"2607.12503","title":"DynTrace: Tracking Dynamic Object Evidence for 4D Spatio-Temporal Reasoning in MLLMs","created":"2026-07-14","cited_by_count":2,"area":"lr"},{"id":"2607.16107","title":"Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos","created":"2026-07-17","cited_by_count":2,"area":"lr"},{"id":"2509.22363","title":"Investigating Faithfulness in Large Audio Language Models","created":"2025-09-26","cited_by_count":1,"area":"lr"},{"id":"2601.04960","title":"A Unified Spoken Language Model with Injected Emotional-Attribution Thinking for Human-like Interaction","created":"2026-01-08","cited_by_count":1,"area":"lr"},{"id":"2604.08003","title":"Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs","created":"2026-04-09","cited_by_count":1,"area":"lr"},{"id":"2604.16617","title":"AVRT: Audio-Visual Reasoning Transfer through Single-Modality Teachers","created":"2026-04-17","cited_by_count":1,"area":"lr"},{"id":"2604.18187","title":"Audio-DeepThinker: Progressive Reasoning-Aware Reinforcement Learning for High-Quality Chain-of-Thought Emergence in Audio Language Models","created":"2026-04-20","cited_by_count":1,"area":"lr"},{"id":"2604.23348","title":"EmoTrans: A Benchmark for Understanding, Reasoning, and Predicting Emotion Transitions in Multimodal LLMs","created":"2026-04-25","cited_by_count":1,"area":"lr"},{"id":"2605.01278","title":"Valley3: Scaling Omni Foundation Models for E-commerce","created":"2026-05-02","cited_by_count":1,"area":"lr"},{"id":"2606.00507","title":"LaSR: Context-Aware Speech Recognition via Latent Reasoning","created":"2026-05-30","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":"2606.12018","title":"MODF-SIR: A Multi-agent Omni-modal Distilled Framework for Social Intelligence Reasoning","created":"2026-06-10","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":"2606.27652","title":"MER-R1: Multimodal Emotion Reasoning via Slow-Fast Thinking Synergy","created":"2026-06-26","cited_by_count":1,"area":"lr"},{"id":"2607.05511","title":"Light-Omni: Reflex over Reasoning in Agentic Video Understanding with Long-Term Memory","created":"2026-07-06","cited_by_count":1,"area":"lr"},{"id":"2607.10238","title":"Benchmarking Dynamic Affective Reasoning: A Viewer-Centric Video Emotion Dataset","created":"2026-07-11","cited_by_count":1,"area":"lr"},{"id":"2608.26432","title":"SpeechGym: An Audio-Native Gym for Training Voice Agents via Reinforcement Learning","created":"2026-08-26","cited_by_count":1,"area":"lr"},{"id":"2609.17416","title":"Never Stop Thinking: Continuous-Time Language Agents","created":"2026-07-11","cited_by_count":1,"area":"lr"},{"id":"2609.19991","title":"AVTrace: Diagnosing Audio-Visual Temporal Reasoning in Omni Models","created":"2026-09-17","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":"2610.01560","title":"AURAL: Adaptive Latent Reasoning with Joint Chunk for Speech Language Models","created":"2026-10-01","cited_by_count":1,"area":"lr"},{"id":"2510.06750","title":"Gold-Switch: Training-Free Superposition of Slow- and Fast- Thinking LLMs","created":"2025-10-08","cited_by_count":0,"area":"lr"},{"id":"2601.18321","title":"Integrating Fine-Grained Audio-Visual Evidence for Robust Multimodal Emotion Reasoning","created":"2026-01-26","cited_by_count":0,"area":"lr"},{"id":"2602.04085","title":"BASS: Benchmarking Audio LMs for Musical Structure and Semantic Reasoning","created":"2026-02-03","cited_by_count":0,"area":"lr"},{"id":"2602.12714","title":"ADEPT: RL-Aligned Agentic Decoding of Emotion via Evidence Probing Tools -- From Consensus Learning to Ambiguity-Driven Emotion Reasoning","created":"2026-02-13","cited_by_count":0,"area":"lr"},{"id":"2603.03944","title":"SCP: Spatial Causal Prediction in Video","created":"2026-03-04","cited_by_count":0,"area":"lr"},{"id":"2603.04415","title":"Dual Tuning for Reasoning Efficacy-Driven Data Curation in Multimodal LLM Training","created":"2026-02-04","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":"2603.25203","title":"Probabilistic Concept Graph Reasoning for Multimodal Misinformation Detection","created":"2026-03-26","cited_by_count":0,"area":"lr"},{"id":"2604.00013","title":"C2F-Thinker: Coarse-to-Fine Reasoning with Hint-Guided Reinforcement Learning for Multimodal Sentiment Analysis","created":"2026-03-10","cited_by_count":0,"area":"lr"},{"id":"2604.02007","title":"Apriel-Reasoner: RL Post-Training for General-Purpose and Efficient Reasoning","created":"2026-04-02","cited_by_count":0,"area":"lr"},{"id":"2604.11424","title":"Bridging What the Model Thinks and How It Speaks: Expressive Speech Generation via Self-Aware Intent-Realization Alignment","created":"2026-04-13","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":"2605.08452","title":"NICE FACT: Diagnosing and Calibrating VLMs in Quantitative Reasoning for Kinematic Physics","created":"2026-05-08","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":"2606.18988","title":"ThinkDeception: A Progressive Reinforcement Learning Framework for Interpretable Multimodal Deception Detection","created":"2026-06-17","cited_by_count":0,"area":"lr"},{"id":"2607.01733","title":"Rethinking Speech-LLM Integration for ASR: Effective Joint Speech-Text Training by Interleaving","created":"2026-07-02","cited_by_count":0,"area":"lr"},{"id":"2607.19932","title":"Efficient Chain-of-Modality Reasoning via Progressive Compression for Spoken Language Models","created":"2026-07-22","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":"2608.24958","title":"Can We Read the Mind of an Audio LLM? A Verbalizable, Multilingual Middle-Layer Workspace","created":"2026-08-25","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":"2608.29120","title":"HEAR Who Said What: Unlocking Speaker-Attributed Reasoning via Counterfactual Voice Grounding","created":"2026-08-29","cited_by_count":0,"area":"lr"},{"id":"2608.31014","title":"Evidence-Bounded Mental Health Reasoning from Heterogeneous Speech Protocols","created":"2026-08-31","cited_by_count":0,"area":"lr"},{"id":"2609.15234","title":"CWM: Controllable White-Box Meta-Prompting for Adaptive Retrieval-Augmented Generation and Reasoning Ability","created":"2026-09-14","cited_by_count":0,"area":"lr"},{"id":"2609.18677","title":"Voice of Reason: Reinforcement Learning for Spoken Math","created":"2026-09-16","cited_by_count":0,"area":"lr"},{"id":"2609.22697","title":"COT-TTS: Audio Context-Aware Text-to-Speech with Chain-of-Thought Reasoning","created":"2026-09-19","cited_by_count":0,"area":"lr"},{"id":"2609.32569","title":"OmniSmartHome: A Multimodal Reasoning Benchmark for Smart-Home Agents","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2609.33338","title":"OPERA: A Unified Omnimodal Progressive Spatio-Temporal Reasoning Agent for Referring Video Segmentation","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.37052","title":"OmniRoute: Mapping Temporal Semantic Evidence to Audio-Visual Token Budgets for Efficient Omnimodal Large Language Models","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2609.37976","title":"$S^3$: Spectral Null-Space Swap Makes Reasoning Models Efficient","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2609.39150","title":"OP-CAD: On-Policy Clean-Audio Distillation for Robust Audio-Visual Reasoning","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2609.39953","title":"Learning to Reason with Compressed Context: Ground-Truth-Free Adaptation of OmniLLMs via Self-Distillation","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.02181","title":"OmniSeek: Native Tool Integration for Multi-turn Audio-Visual Reasoning","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.02819","title":"Text-Centric Post-Training for Omni-Modal Reasoning","created":"2026-10-02","cited_by_count":0,"area":"lr"},{"id":"2610.11310","title":"FloorSAV: Elucidating Spatial Audio-Visual Context with 2D Floormap for AV-LLMs","created":"2026-10-08","cited_by_count":0,"area":"lr"},{"id":"2610.11918","title":"From Surface to Depth: Towards Cognitive Appraisal Reasoning in Multimodal Emotion Understanding","created":"2026-10-08","cited_by_count":0,"area":"lr"},{"id":"2610.12458","title":"OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning","created":"2026-10-08","cited_by_count":0,"area":"lr"},{"id":"2610.13081","title":"SWEAR: Section-Wise Efficient Audio Reasoning via Self-Rated Difficulty","created":"2026-10-09","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}