{"list":"other","total":78,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242},{"id":"2408.01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","created":"2024-08-03","cited_by_count":1079},{"id":"2403.20330","title":"Are We on the Right Way for Evaluating Large Vision-Language Models?","created":"2024-03-29","cited_by_count":914},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839},{"id":"2305.14233","title":"Enhancing Chat Language Models by Scaling High-quality Instructional Conversations","created":"2023-05-23","cited_by_count":839},{"id":"2406.16860","title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","created":"2024-06-24","cited_by_count":838},{"id":"1603.07396","title":"A Diagram Is Worth A Dozen Images","created":"2016-03-24","cited_by_count":804},{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771},{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623},{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615},{"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},{"id":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568},{"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":"2407.11691","title":"VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models","created":"2024-07-16","cited_by_count":455},{"id":"2305.19860","title":"A Survey on Large Language Models for Recommendation","created":"2023-05-31","cited_by_count":379},{"id":"2402.00253","title":"A Survey on Hallucination in Large Vision-Language Models","created":"2024-02-01","cited_by_count":357},{"id":"2305.16355","title":"PandaGPT: One Model To Instruction-Follow Them All","created":"2023-05-25","cited_by_count":334},{"id":"2407.05407","title":"CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens","created":"2024-07-07","cited_by_count":334},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333},{"id":"2312.17172","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action","created":"2023-12-28","cited_by_count":302},{"id":"2309.11499","title":"DreamLLM: Synergistic Multimodal Comprehension and Creation","created":"2023-09-20","cited_by_count":297},{"id":"2104.00355","title":"Speech Resynthesis from Discrete Disentangled Self-Supervised Representations","created":"2021-04-01","cited_by_count":243},{"id":"2412.02612","title":"GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot","created":"2024-12-03","cited_by_count":224},{"id":"2402.12226","title":"AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling","created":"2024-02-19","cited_by_count":217},{"id":"2312.15185","title":"emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation","created":"2023-12-23","cited_by_count":205},{"id":"2110.03370","title":"WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition","created":"2021-10-07","cited_by_count":197},{"id":"2311.13165","title":"Multimodal Large Language Models: A Survey","created":"2023-11-22","cited_by_count":195},{"id":"2312.03700","title":"OneLLM: One Framework to Align All Modalities with Language","created":"2023-12-06","cited_by_count":187},{"id":"2110.07205","title":"SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing","created":"2021-10-14","cited_by_count":180},{"id":"2202.10936","title":"A Survey of Vision-Language Pre-Trained Models","created":"2022-02-18","cited_by_count":177},{"id":"2408.05211","title":"VITA: Towards Open-Source Interactive Omni Multimodal LLM","created":"2024-08-09","cited_by_count":173},{"id":"2409.06666","title":"LLaMA-Omni: Seamless Speech Interaction with Large Language Models","created":"2024-09-10","cited_by_count":173},{"id":"2409.00750","title":"MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer","created":"2024-09-01","cited_by_count":161},{"id":"2411.00774","title":"Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM","created":"2024-11-01","cited_by_count":141},{"id":"2310.14414","title":"Vision Language Models in Autonomous Driving: A Survey and Outlook","created":"2023-10-22","cited_by_count":126},{"id":"2404.00656","title":"WavLLM: Towards Robust and Adaptive Speech Large Language Model","created":"2024-03-31","cited_by_count":109},{"id":"2406.15704","title":"video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models","created":"2024-06-22","cited_by_count":102},{"id":"2409.15272","title":"OmniBench: Towards The Future of Universal Omni-Language Models","created":"2024-09-23","cited_by_count":102},{"id":"2404.14387","title":"A Survey on Self-Evolution of Large Language Models","created":"2024-04-22","cited_by_count":91},{"id":"2410.03751","title":"Recent Advances in Speech Language Models: A Survey","created":"2024-10-01","cited_by_count":87},{"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":"2410.17799","title":"OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation","created":"2024-10-23","cited_by_count":60},{"id":"2308.12038","title":"Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages","created":"2023-08-23","cited_by_count":52},{"id":"2305.08386","title":"PLIP: Language-Image Pre-training for Person Representation Learning","created":"2023-05-15","cited_by_count":49},{"id":"2412.02611","title":"AV-Odyssey Bench: Can Your Multimodal LLMs Really Understand Audio-Visual Information?","created":"2024-12-03","cited_by_count":47},{"id":"2409.18042","title":"EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions","created":"2024-09-26","cited_by_count":45},{"id":"2409.20007","title":"DeSTA2: Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data","created":"2024-09-30","cited_by_count":45},{"id":"2312.10302","title":"One-Shot Learning as Instruction Data Prospector for Large Language Models","created":"2023-12-16","cited_by_count":43},{"id":"2409.05840","title":"MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct","created":"2024-09-09","cited_by_count":42},{"id":"2410.08565","title":"Baichuan-Omni Technical Report","created":"2024-10-11","cited_by_count":42},{"id":"2403.14774","title":"Few-Shot Adversarial Prompt Learning on Vision-Language Models","created":"2024-03-21","cited_by_count":39},{"id":"2402.01591","title":"BAT: Learning to Reason about Spatial Sounds with Large Language Models","created":"2024-02-02","cited_by_count":36},{"id":"2405.15232","title":"DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception","created":"2024-05-24","cited_by_count":32},{"id":"2409.10157","title":"Emo-DPO: Controllable Emotional Speech Synthesis through Direct Preference Optimization","created":"2024-09-16","cited_by_count":32},{"id":"2411.18363","title":"ChatRex: Taming Multimodal LLM for Joint Perception and Understanding","created":"2024-11-27","cited_by_count":30},{"id":"2205.15060","title":"Duplex Conversation: Towards Human-like Interaction in Spoken Dialogue Systems","created":"2022-05-30","cited_by_count":28},{"id":"2310.10873","title":"IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models","created":"2023-10-16","cited_by_count":27},{"id":"2406.03049","title":"StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning","created":"2024-06-05","cited_by_count":21},{"id":"2402.09378","title":"MobileSpeech: A Fast and High-Fidelity Framework for Mobile Zero-Shot Text-to-Speech","created":"2024-02-14","cited_by_count":15},{"id":"2406.18294","title":"Hierarchical Context Pruning: Optimizing Real-World Code Completion with Repository-Level Pretrained Code LLMs","created":"2024-06-26","cited_by_count":13},{"id":"2409.07556","title":"SSR-Speech: Towards Stable, Safe and Robust Zero-shot Text-based Speech Editing and Synthesis","created":"2024-09-11","cited_by_count":13},{"id":"2406.06937","title":"A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Speech Translation","created":"2024-06-11","cited_by_count":10},{"id":"2412.05243","title":"CompCap: Improving Multimodal Large Language Models with Composite Captions","created":"2024-12-06","cited_by_count":8},{"id":"2409.12139","title":"Takin: A Cohort of Superior Quality Zero-shot Speech Generation Models","created":"2024-09-18","cited_by_count":7}],"next_cursor":null}