{"list":"other","total":55,"rows":[{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004},{"id":"2507.18071","title":"Group Sequence Policy Optimization","created":"2025-07-24","cited_by_count":835},{"id":"2503.20215","title":"Qwen2.5-Omni Technical Report","created":"2025-03-26","cited_by_count":736},{"id":"2402.14804","title":"Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset","created":"2024-02-22","cited_by_count":526},{"id":"2509.17765","title":"Qwen3-Omni Technical Report","created":"2025-09-22","cited_by_count":497},{"id":"2205.12446","title":"FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech","created":"2022-05-25","cited_by_count":469},{"id":"2405.14573","title":"AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents","created":"2024-05-23","cited_by_count":468},{"id":"2406.08035","title":"LVBench: An Extreme Long Video Understanding Benchmark","created":"2024-06-12","cited_by_count":410},{"id":"2509.16941","title":"SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?","created":"2025-09-21","cited_by_count":279},{"id":"2406.18521","title":"CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs","created":"2024-06-26","cited_by_count":234},{"id":"2410.17196","title":"VoiceBench: Benchmarking LLM-Based Voice Assistants","created":"2024-10-22","cited_by_count":200},{"id":"2110.03370","title":"WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition","created":"2021-10-07","cited_by_count":197},{"id":"2507.02833","title":"Generalizing Verifiable Instruction Following","created":"2025-07-03","cited_by_count":194},{"id":"2604.15804","title":"Qwen3.5-Omni Technical Report","created":"2026-04-17","cited_by_count":174},{"id":"2502.04326","title":"WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs","created":"2025-02-06","cited_by_count":155},{"id":"2411.03628","title":"StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding","created":"2024-11-06","cited_by_count":144},{"id":"2505.13032","title":"MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix","created":"2025-05-19","cited_by_count":117},{"id":"2505.17862","title":"Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalities","created":"2025-05-23","cited_by_count":110},{"id":"2506.04779","title":"MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark","created":"2025-06-05","cited_by_count":103},{"id":"2606.30406","title":"MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training","created":"2026-06-29","cited_by_count":72},{"id":"2110.07393","title":"M2MeT: The ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Challenge","created":"2021-10-14","cited_by_count":71},{"id":"2512.12730","title":"NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents","created":"2025-12-14","cited_by_count":65},{"id":"2604.06132","title":"Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents","created":"2026-04-07","cited_by_count":64},{"id":"2104.03603","title":"AISHELL-4: An Open Source Dataset for Speech Enhancement, Separation, Recognition and Speaker Diarization in Conference Scenario","created":"2021-04-08","cited_by_count":60},{"id":"2510.10689","title":"OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs","created":"2025-10-12","cited_by_count":59},{"id":"2607.00248","title":"Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity","created":"2026-06-30","cited_by_count":58},{"id":"2604.05015","title":"Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding","created":"2026-04-06","cited_by_count":55},{"id":"2203.16844","title":"Open Source MagicData-RAMC: A Rich Annotated Mandarin Conversational(RAMC) Speech Dataset","created":"2022-03-31","cited_by_count":40},{"id":"2605.10912","title":"WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation","created":"2026-05-11","cited_by_count":37},{"id":"2503.19951","title":"Audio-centric Video Understanding Benchmark without Text Shortcut","created":"2025-03-25","cited_by_count":36},{"id":"2608.30320","title":"On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability","created":"2026-08-31","cited_by_count":35},{"id":"2510.12720","title":"Omni-Captioner: Data Pipeline, Models, and Benchmark for Omni Detailed Perception","created":"2025-10-14","cited_by_count":30},{"id":"2507.09313","title":"ProactiveVideoQA: A Comprehensive Benchmark Evaluating Proactive Interactions in Video Large Language Models","created":"2025-07-12","cited_by_count":27},{"id":"2603.19217","title":"LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs","created":"2026-03-19","cited_by_count":24},{"id":"2512.02231","title":"See, Hear, and Understand: Benchmarking Audiovisual Human Speech Understanding in Multimodal Large Language Models","created":"2025-12-01","cited_by_count":20},{"id":"2512.14865","title":"Audio MultiChallenge: A Multi-Turn Evaluation of Spoken Dialogue Systems on Natural Human Interaction","created":"2025-12-16","cited_by_count":19},{"id":"2512.12772","title":"JointAVBench: A Benchmark for Joint Audio-Visual Reasoning Evaluation","created":"2025-12-14","cited_by_count":17},{"id":"2504.00369","title":"Are you really listening? Boosting Perceptual Awareness in Music-QA Benchmarks","created":"2025-04-01","cited_by_count":16},{"id":"2603.26648","title":"Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification","created":"2026-03-27","cited_by_count":16},{"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},{"id":"2506.21875","title":"WildSpeech-Bench: Benchmarking End-to-End SpeechLLMs in the Wild","created":"2025-06-27","cited_by_count":13},{"id":"2509.13785","title":"Summary on The Multilingual Conversational Speech Language Model Challenge: Datasets, Tasks, Baselines, and Methods","created":"2025-09-17","cited_by_count":10},{"id":"2503.19356","title":"Can Vision-Language Models Answer Face to Face Questions in the Real-World?","created":"2025-03-25","cited_by_count":7},{"id":"2604.13023","title":"SpotSound: Enhancing Large Audio-Language Models with Fine-Grained Temporal Grounding","created":"2026-04-14","cited_by_count":5},{"id":"2605.29300","title":"MusTBench: Benchmarking and Advancing Temporal Grounding in Music LLMs","created":"2026-05-28","cited_by_count":2},{"id":"2606.08572","title":"OmniCap-IF: Benchmarking and Improving Instruction Following Abilities for Omni-Video Captioning","created":"2026-06-07","cited_by_count":2},{"id":"2607.08768","title":"UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks","created":"2026-07-09","cited_by_count":2},{"id":"2608.26431","title":"LongAudioSpan: Spanning the Duration and Depth of Audio Comprehension","created":"2026-08-26","cited_by_count":2},{"id":"2609.22452","title":"Vox-Infinity: Benchmarking the Limits of Long-Context Spoken Language Models","created":"2026-09-18","cited_by_count":2},{"id":"2609.23407","title":"OmniEcho: Audio-Visual Spatial Understanding for Omni-Modal Embodied Agents","created":"2026-09-20","cited_by_count":2},{"id":"2603.27877","title":"HumMusQA: A Human-written Music Understanding QA Benchmark Dataset","created":"2026-03-29","cited_by_count":1},{"id":"2609.21392","title":"Omni Demand Understanding: A Benchmark for Contextual User-Intent Inference in Multimodal Interaction","created":"2026-09-18","cited_by_count":1},{"id":"2609.23416","title":"MuLA-Bench: A Multilingual Long-Form Audio Understanding Benchmark via Multi-Tier Auditing","created":"2026-09-20","cited_by_count":1},{"id":"2609.23417","title":"Omni2Web: Benchmarking Audiovisual Website Development","created":"2026-09-20","cited_by_count":1}],"next_cursor":null}