{"total":29,"rows":[{"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":"2508.11630","title":"Thyme: Think Beyond Images","created":"2025-08-15","cited_by_count":167,"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":"2501.04686","title":"Unlocking Multimodal Mathematical Reasoning via Process Reward Model","created":"2025-01-08","cited_by_count":65,"area":"lr"},{"id":"2505.10557","title":"MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning","created":"2025-05-15","cited_by_count":45,"area":"lr"},{"id":"2503.13444","title":"VideoMind: A Chain-of-LoRA Agent for Temporal-Grounded Video Reasoning","created":"2025-03-17","cited_by_count":43,"area":"lr"},{"id":"2409.18938","title":"From Seconds to Hours: Reviewing MultiModal Large Language Models on Comprehensive Long Video Understanding","created":"2024-09-27","cited_by_count":30,"area":"lr"},{"id":"2505.24714","title":"FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning Evaluation","created":"2025-05-30","cited_by_count":30,"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":"2501.04670","title":"Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs","created":"2025-01-08","cited_by_count":16,"area":"lr"},{"id":"2508.03100","title":"AVATAR: Reinforcement Learning to See, Hear, and Reason Over Video","created":"2025-08-05","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":"2503.23219","title":"Aurelia: Test-time Reasoning Distillation in Audio-Visual LLMs","created":"2025-03-29","cited_by_count":9,"area":"lr"},{"id":"2504.00487","title":"FortisAVQA and MAVEN: a Benchmark Dataset and Debiasing Framework for Robust Multimodal Reasoning","created":"2025-04-01","cited_by_count":8,"area":"lr"},{"id":"2508.07470","title":"AURA: A Fine-Grained Benchmark and Decomposed Metric for Audio-Visual Reasoning","created":"2025-08-10","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":"2411.03314","title":"MME-Finance: A Multimodal Finance Benchmark for Expert-level Understanding and Reasoning","created":"2024-11-05","cited_by_count":7,"area":"lr"},{"id":"2411.00890","title":"Rethinking Scale: The Efficacy of Fine-Tuned Open-Source LLMs in Large-Scale Reproducible Social Science Research","created":"2024-10-31","cited_by_count":6,"area":"lr"},{"id":"2505.24182","title":"Seeing is Not Reasoning: MVPBench for Graph-based Evaluation of Multi-path Visual Physical CoT","created":"2025-05-30","cited_by_count":6,"area":"lr"},{"id":"2504.08809","title":"Decoupling Contrastive Decoding: Robust Hallucination Mitigation in Multimodal Large Language Models","created":"2025-04-09","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":"2502.13789","title":"From Correctness to Comprehension: AI Agents for Personalized Error Diagnosis in Education","created":"2025-02-19","cited_by_count":4,"area":"lr"},{"id":"2503.22208","title":"DeepSound-V1: Start to Think Step-by-Step in the Audio Generation from Videos","created":"2025-03-28","cited_by_count":4,"area":"lr"},{"id":"2512.09354","title":"Video-QTR: Query-Driven Temporal Reasoning Framework for Lightweight Video Understanding","created":"2025-12-10","cited_by_count":4,"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":"2609.17248","title":"Video-HolmesV2: Can MLLMs Reason with Spatio-Temporal Audio-Visual Evidence in Long Videos?","created":"2026-09-15","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"}],"next_cursor":null}