{"list":"other","total":54,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2409.12122","title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","created":"2024-09-18","cited_by_count":1090},{"id":"2211.06687","title":"Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation","created":"2022-11-12","cited_by_count":719},{"id":"2210.03493","title":"Automatic Chain of Thought Prompting in Large Language Models","created":"2022-10-07","cited_by_count":688},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615},{"id":"2407.10759","title":"Qwen2-Audio Technical Report","created":"2024-07-15","cited_by_count":560},{"id":"2305.11000","title":"SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities","created":"2023-05-18","cited_by_count":529},{"id":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506},{"id":"2411.10440","title":"LLaVA-CoT: Let Vision Language Models Reason Step-by-Step","created":"2024-11-15","cited_by_count":454},{"id":"2503.10615","title":"R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization","created":"2025-03-13","cited_by_count":370},{"id":"2010.00475","title":"FSD50K: An Open Dataset of Human-Labeled Sound Events","created":"2020-10-01","cited_by_count":342},{"id":"2305.16355","title":"PandaGPT: One Model To Instruction-Follow Them All","created":"2023-05-25","cited_by_count":334},{"id":"2301.13379","title":"Faithful Chain-of-Thought Reasoning","created":"2023-01-31","cited_by_count":288},{"id":"2303.17395","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","created":"2023-03-30","cited_by_count":267},{"id":"2409.12183","title":"To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning","created":"2024-09-18","cited_by_count":263},{"id":"2502.14768","title":"Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning","created":"2025-02-20","cited_by_count":262},{"id":"2504.18425","title":"Kimi-Audio Technical Report","created":"2025-04-25","cited_by_count":222},{"id":"2305.11834","title":"Pengi: An Audio Language Model for Audio Tasks","created":"2023-05-19","cited_by_count":220},{"id":"2305.10790","title":"Listen, Think, and Understand","created":"2023-05-18","cited_by_count":209},{"id":"2501.01957","title":"VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction","created":"2025-01-03","cited_by_count":197},{"id":"2005.12729","title":"Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO","created":"2020-05-25","cited_by_count":186},{"id":"2402.01831","title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","created":"2024-02-02","cited_by_count":186},{"id":"2501.03230","title":"Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition","created":"2024-05-07","cited_by_count":153},{"id":"2412.05237","title":"MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale","created":"2024-12-06","cited_by_count":127},{"id":"2410.11190","title":"Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities","created":"2024-10-15","cited_by_count":109},{"id":"2507.16632","title":"Step-Audio 2 Technical Report","created":"2025-07-22","cited_by_count":105},{"id":"2305.18802","title":"LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpus","created":"2023-05-30","cited_by_count":101},{"id":"2309.14405","title":"Joint Audio and Speech Understanding","created":"2023-09-25","cited_by_count":100},{"id":"2311.08355","title":"Mustango: Toward Controllable Text-to-Music Generation","created":"2023-11-14","cited_by_count":100},{"id":"2307.16372","title":"LP-MusicCaps: LLM-Based Pseudo Music Captioning","created":"2023-07-31","cited_by_count":83},{"id":"2501.06282","title":"MinMo: A Multimodal Large Language Model for Seamless Voice Interaction","created":"2025-01-10","cited_by_count":79},{"id":"2308.11276","title":"Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning","created":"2023-08-22","cited_by_count":77},{"id":"2411.17558","title":"Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey","created":"2024-11-26","cited_by_count":76},{"id":"2405.08295","title":"SpeechVerse: A Large-scale Generalizable Audio Language Model","created":"2024-05-14","cited_by_count":63},{"id":"2505.10832","title":"Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL","created":"2025-05-16","cited_by_count":62},{"id":"2507.02768","title":"DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment","created":"2025-07-03","cited_by_count":50},{"id":"2505.09439","title":"Omni-R1: Do You Really Need Audio to Fine-Tune Your Audio LLM?","created":"2025-05-14","cited_by_count":46},{"id":"2505.17018","title":"SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward","created":"2025-05-22","cited_by_count":45},{"id":"2406.04321","title":"VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling","created":"2024-06-06","cited_by_count":40},{"id":"1911.09655","title":"Temporal Reasoning via Audio Question Answering","created":"2019-11-21","cited_by_count":39},{"id":"2406.08402","title":"Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models","created":"2024-06-12","cited_by_count":31},{"id":"2309.09836","title":"RECAP: Retrieval-Augmented Audio Captioning","created":"2023-09-18","cited_by_count":27},{"id":"2411.18953","title":"AudioSetCaps: An Enriched Audio-Caption Dataset using Automated Generation Pipeline with Large Audio and Language Models","created":"2024-11-28","cited_by_count":21},{"id":"2404.12020","title":"Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering","created":"2024-04-18","cited_by_count":18},{"id":"2506.12285","title":"CMI-Bench: A Comprehensive Benchmark for Evaluating Music Instruction Following","created":"2025-06-14","cited_by_count":17},{"id":"2509.21060","title":"Measuring Audio's Impact on Correctness: Audio-Contribution-Aware Post-Training of Large Audio Language Models","created":"2025-09-25","cited_by_count":15},{"id":"2205.05357","title":"Beyond the Status Quo: A Contemporary Survey of Advances and Challenges in Audio Captioning","created":"2022-05-11","cited_by_count":10},{"id":"2506.11350","title":"GLAP: General contrastive audio-text pretraining across domains and languages","created":"2025-06-12","cited_by_count":10},{"id":"2407.06947","title":"Audio-Language Datasets of Scenes and Events: A Survey","created":"2024-07-09","cited_by_count":3},{"id":"2602.03023","title":"Rethinking Music Captioning with Music Metadata LLMs","created":"2026-02-03","cited_by_count":2}],"next_cursor":null}