{"total":4057,"rows":[{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439,"area":"agents"},{"id":"2308.02490","title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","created":"2023-08-04","cited_by_count":1239,"area":"mllm"},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173,"area":null},{"id":"2306.13649","title":"On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes","created":"2023-06-23","cited_by_count":939,"area":"synth"},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857,"area":null},{"id":"2503.20215","title":"Qwen2.5-Omni Technical Report","created":"2025-03-26","cited_by_count":736,"area":"lr"},{"id":"2301.10226","title":"A Watermark for Large Language Models","created":"2023-01-24","cited_by_count":725,"area":"safety"},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648,"area":null},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644,"area":"diffusion"},{"id":"2311.07919","title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","created":"2023-11-14","cited_by_count":608,"area":null},{"id":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568,"area":null},{"id":"2407.10759","title":"Qwen2-Audio Technical Report","created":"2024-07-15","cited_by_count":560,"area":null},{"id":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506,"area":null},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490,"area":null},{"id":"2305.13516","title":"Scaling Speech Technology to 1,000+ Languages","created":"2023-05-22","cited_by_count":411,"area":null},{"id":"2312.02051","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","created":"2023-12-04","cited_by_count":406,"area":"mllm"},{"id":"2302.10866","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","created":"2023-02-21","cited_by_count":393,"area":null},{"id":"2306.15687","title":"Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale","created":"2023-06-23","cited_by_count":379,"area":null},{"id":"2410.06885","title":"F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching","created":"2024-10-09","cited_by_count":361,"area":"diffusion"},{"id":"2306.12925","title":"AudioPaLM: A Large Language Model That Can Speak and Listen","created":"2023-06-22","cited_by_count":343,"area":null},{"id":"2403.15377","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","created":"2024-03-22","cited_by_count":317,"area":null},{"id":"2312.06662","title":"Photorealistic Video Generation with Diffusion Models","created":"2023-12-11","cited_by_count":306,"area":"diffusion"},{"id":"2409.02060","title":"OLMoE: Open Mixture-of-Experts Language Models","created":"2024-09-03","cited_by_count":301,"area":"moe"},{"id":"2306.17439","title":"Provable Robust Watermarking for AI-Generated Text","created":"2023-06-30","cited_by_count":299,"area":"safety"},{"id":"2302.10149","title":"Poisoning Web-Scale Training Datasets is Practical","created":"2023-02-20","cited_by_count":290,"area":null},{"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":"2412.10117","title":"CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models","created":"2024-12-13","cited_by_count":288,"area":"diffusion"},{"id":"2401.13601","title":"MM-LLMs: Recent Advances in MultiModal Large Language Models","created":"2024-01-24","cited_by_count":278,"area":"mllm"},{"id":"2304.12995","title":"AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head","created":"2023-04-25","cited_by_count":265,"area":null},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2309.17425","title":"Data Filtering Networks","created":"2023-09-29","cited_by_count":250,"area":null},{"id":"2303.01037","title":"Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages","created":"2023-03-02","cited_by_count":231,"area":null},{"id":"2504.18425","title":"Kimi-Audio Technical Report","created":"2025-04-25","cited_by_count":222,"area":null},{"id":"2502.19417","title":"Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models","created":"2025-02-26","cited_by_count":221,"area":null},{"id":"2402.07729","title":"AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension","created":"2024-02-12","cited_by_count":220,"area":null},{"id":"2402.12226","title":"AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling","created":"2024-02-19","cited_by_count":217,"area":"mllm"},{"id":"2302.12095","title":"On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective","created":"2023-02-22","cited_by_count":211,"area":null},{"id":"2412.04453","title":"NaVILA: Legged Robot Vision-Language-Action Model for Navigation","created":"2024-12-05","cited_by_count":211,"area":"vla"},{"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":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2407.03168","title":"LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control","created":"2024-07-03","cited_by_count":206,"area":null},{"id":"2312.15185","title":"emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation","created":"2023-12-23","cited_by_count":205,"area":null},{"id":"2407.05361","title":"Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation","created":"2024-07-07","cited_by_count":204,"area":null},{"id":"2410.17196","title":"VoiceBench: Benchmarking LLM-Based Voice Assistants","created":"2024-10-22","cited_by_count":200,"area":null},{"id":"2407.03320","title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","created":"2024-07-03","cited_by_count":195,"area":"mllm"},{"id":"2306.11207","title":"Quilt-1M: One Million Image-Text Pairs for Histopathology","created":"2023-06-20","cited_by_count":194,"area":null},{"id":"2306.04634","title":"On the Reliability of Watermarks for Large Language Models","created":"2023-06-07","cited_by_count":189,"area":"safety"},{"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,"area":null},{"id":"2303.16434","title":"TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIs","created":"2023-03-29","cited_by_count":184,"area":null},{"id":"2406.04904","title":"XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model","created":"2024-06-07","cited_by_count":179,"area":null},{"id":"2409.06666","title":"LLaMA-Omni: Seamless Speech Interaction with Large Language Models","created":"2024-09-10","cited_by_count":173,"area":null},{"id":"2306.09093","title":"Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration","created":"2023-06-15","cited_by_count":172,"area":"mllm"},{"id":"2505.17589","title":"CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training","created":"2025-05-23","cited_by_count":150,"area":"diffusion"},{"id":"2307.03917","title":"On decoder-only architecture for speech-to-text and large language model integration","created":"2023-07-08","cited_by_count":145,"area":null},{"id":"2309.03199","title":"Matcha-TTS: A fast TTS architecture with conditional flow matching","created":"2023-09-06","cited_by_count":145,"area":"diffusion"},{"id":"2403.03883","title":"SaulLM-7B: A pioneering Large Language Model for Law","created":"2024-03-06","cited_by_count":142,"area":null},{"id":"2401.05856","title":"Seven Failure Points When Engineering a Retrieval Augmented Generation System","created":"2024-01-11","cited_by_count":139,"area":"rag"},{"id":"2411.13093","title":"Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension","created":"2024-11-20","cited_by_count":138,"area":"rag"},{"id":"2405.05945","title":"Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers","created":"2024-05-09","cited_by_count":137,"area":"diffusion"},{"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":"2510.26583","title":"Emu3.5: Native Multimodal Models are World Learners","created":"2025-10-30","cited_by_count":132,"area":"wm"},{"id":"2303.03329","title":"End-to-End Speech Recognition: A Survey","created":"2023-03-03","cited_by_count":129,"area":null},{"id":"2303.16104","title":"Hallucinations in Large Multilingual Translation Models","created":"2023-03-28","cited_by_count":129,"area":null},{"id":"2402.05755","title":"Spirit LM: Interleaved Spoken and Written Language Model","created":"2024-02-08","cited_by_count":126,"area":"mllm"},{"id":"2403.12910","title":"Yell At Your Robot: Improving On-the-Fly from Language Corrections","created":"2024-03-19","cited_by_count":124,"area":"mllm"},{"id":"2407.04051","title":"FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs","created":"2024-07-04","cited_by_count":122,"area":null},{"id":"2403.16973","title":"VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild","created":"2024-03-25","cited_by_count":120,"area":null},{"id":"2504.08528","title":"On The Landscape of Spoken Language Models: A Comprehensive Survey","created":"2025-04-11","cited_by_count":118,"area":null},{"id":"2601.21337","title":"Qwen3-ASR Technical Report","created":"2026-01-29","cited_by_count":118,"area":null},{"id":"2305.11176","title":"Instruct2Act: Mapping Multi-modality Instructions to Robotic Actions with Large Language Model","created":"2023-05-18","cited_by_count":116,"area":null},{"id":"2405.08813","title":"CinePile: A Long Video Question Answering Dataset and Benchmark","created":"2024-05-14","cited_by_count":114,"area":null},{"id":"2503.01710","title":"Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens","created":"2025-03-03","cited_by_count":113,"area":null},{"id":"2306.11706","title":"RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation","created":"2023-06-20","cited_by_count":111,"area":"agents"},{"id":"2501.15368","title":"Baichuan-Omni-1.5 Technical Report","created":"2025-01-26","cited_by_count":111,"area":null},{"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":"2404.00656","title":"WavLLM: Towards Robust and Adaptive Speech Large Language Model","created":"2024-03-31","cited_by_count":109,"area":null},{"id":"2308.11466","title":"SONAR: Sentence-Level Multimodal and Language-Agnostic Representations","created":"2023-08-22","cited_by_count":108,"area":null},{"id":"2405.11273","title":"Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts","created":"2024-05-18","cited_by_count":108,"area":"mllm"},{"id":"2507.16632","title":"Step-Audio 2 Technical Report","created":"2025-07-22","cited_by_count":105,"area":null},{"id":"2502.04144","title":"HD-EPIC: A Highly-Detailed Egocentric Video Dataset","created":"2025-02-06","cited_by_count":104,"area":null},{"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":"2406.15704","title":"video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models","created":"2024-06-22","cited_by_count":102,"area":null},{"id":"2409.15272","title":"OmniBench: Towards The Future of Universal Omni-Language Models","created":"2024-09-23","cited_by_count":102,"area":"mllm"},{"id":"2305.13009","title":"Textually Pretrained Speech Language Models","created":"2023-05-22","cited_by_count":101,"area":null},{"id":"2309.09510","title":"Dynamic-SUPERB: Towards A Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark for Speech","created":"2023-09-18","cited_by_count":101,"area":null},{"id":"2309.14405","title":"Joint Audio and Speech Understanding","created":"2023-09-25","cited_by_count":100,"area":null},{"id":"2407.01603","title":"A Review of Large Language Models and Autonomous Agents in Chemistry","created":"2024-06-26","cited_by_count":99,"area":"agents"},{"id":"2306.08640","title":"AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn","created":"2023-06-14","cited_by_count":97,"area":null},{"id":"2305.05662","title":"InternGPT: Solving Vision-Centric Tasks by Interacting with ChatGPT Beyond Language","created":"2023-05-09","cited_by_count":96,"area":null},{"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":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2503.03803","title":"EgoLife: Towards Egocentric Life Assistant","created":"2025-03-05","cited_by_count":91,"area":null},{"id":"2311.00430","title":"Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling","created":"2023-11-01","cited_by_count":90,"area":"distill"},{"id":"2506.21619","title":"IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech","created":"2025-06-23","cited_by_count":90,"area":null},{"id":"2402.08846","title":"An Embarrassingly Simple Approach for LLM with Strong ASR Capacity","created":"2024-02-13","cited_by_count":88,"area":null},{"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":"2305.16107","title":"VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translation","created":"2023-05-25","cited_by_count":87,"area":null},{"id":"2308.16692","title":"SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models","created":"2023-08-31","cited_by_count":87,"area":null},{"id":"2410.03751","title":"Recent Advances in Speech Language Models: A Survey","created":"2024-10-01","cited_by_count":87,"area":null},{"id":"2505.04512","title":"HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation","created":"2025-05-07","cited_by_count":87,"area":null}],"next_cursor":"100"}