{"list":"other","total":96,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"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":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"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":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"2504.10479","title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","created":"2025-04-14","cited_by_count":1834},{"id":"2308.00352","title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","created":"2023-08-01","cited_by_count":1808},{"id":"2306.13394","title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","created":"2023-06-23","cited_by_count":1652},{"id":"2303.17760","title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","created":"2023-03-31","cited_by_count":1395},{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267},{"id":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","created":"2022-07-12","cited_by_count":1081},{"id":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062},{"id":"2305.13301","title":"Training Diffusion Models with Reinforcement Learning","created":"2023-05-22","cited_by_count":982},{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963},{"id":"2310.12036","title":"A General Theoretical Paradigm to Understand Learning from Human Preferences","created":"2023-10-18","cited_by_count":912},{"id":"1806.05622","title":"VoxCeleb2: Deep Speaker Recognition","created":"2018-06-14","cited_by_count":875},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"2402.01680","title":"Large Language Model based Multi-Agents: A Survey of Progress and Challenges","created":"2024-01-21","cited_by_count":769},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708},{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680},{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615},{"id":"2412.10302","title":"DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding","created":"2024-12-13","cited_by_count":572},{"id":"1906.02467","title":"ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering","created":"2019-06-06","cited_by_count":561},{"id":"2401.01335","title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","created":"2024-01-02","cited_by_count":557},{"id":"2305.03726","title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","created":"2023-05-05","cited_by_count":550},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542},{"id":"2503.01743","title":"Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs","created":"2025-03-03","cited_by_count":521},{"id":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518},{"id":"2509.17765","title":"Qwen3-Omni Technical Report","created":"2025-09-22","cited_by_count":497},{"id":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"2212.04088","title":"LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models","created":"2022-12-08","cited_by_count":462},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"1704.04497","title":"TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering","created":"2017-04-14","cited_by_count":378},{"id":"2505.07062","title":"Seed1.5-VL Technical Report","created":"2025-05-11","cited_by_count":373},{"id":"2403.00476","title":"TempCompass: Do Video LLMs Really Understand Videos?","created":"2024-03-01","cited_by_count":363},{"id":"2005.00200","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","created":"2020-05-01","cited_by_count":362},{"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":"2306.17107","title":"LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding","created":"2023-06-29","cited_by_count":274},{"id":"2402.01306","title":"KTO: Model Alignment as Prospect Theoretic Optimization","created":"2024-02-02","cited_by_count":264},{"id":"2304.07590","title":"Self-collaboration Code Generation via ChatGPT","created":"2023-04-15","cited_by_count":258},{"id":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213},{"id":"2404.03715","title":"Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences","created":"2024-04-04","cited_by_count":178},{"id":"2408.05211","title":"VITA: Towards Open-Source Interactive Omni Multimodal LLM","created":"2024-08-09","cited_by_count":173},{"id":"2501.04001","title":"Sa2VA: Marrying SAM2 with MLLM for Dense Grounded Understanding of Images and Videos","created":"2025-01-07","cited_by_count":159},{"id":"2406.11704","title":"Nemotron-4 340B Technical Report","created":"2024-06-17","cited_by_count":144},{"id":"2407.05600","title":"GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing","created":"2024-07-08","cited_by_count":133},{"id":"2410.01257","title":"HelpSteer2-Preference: Complementing Ratings with Preferences","created":"2024-10-02","cited_by_count":130},{"id":"2407.11325","title":"VISA: Reasoning Video Object Segmentation via Large Language Models","created":"2024-07-16","cited_by_count":127},{"id":"2405.08813","title":"CinePile: A Long Video Question Answering Dataset and Benchmark","created":"2024-05-14","cited_by_count":114},{"id":"2306.05179","title":"M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models","created":"2023-06-08","cited_by_count":110},{"id":"2311.16103","title":"Video-Bench: A Comprehensive Benchmark and Toolkit for Evaluating Video-based Large Language Models","created":"2023-11-27","cited_by_count":107},{"id":"2406.15704","title":"video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models","created":"2024-06-22","cited_by_count":102},{"id":"1901.01342","title":"AVA-ActiveSpeaker: An Audio-Visual Dataset for Active Speaker Detection","created":"2019-01-05","cited_by_count":83},{"id":"2012.11583","title":"Semantic Audio-Visual Navigation","created":"2020-12-21","cited_by_count":82},{"id":"2007.01216","title":"Spot the conversation: speaker diarisation in the wild","created":"2020-07-02","cited_by_count":79},{"id":"2401.10727","title":"MLLM-Tool: A Multimodal Large Language Model For Tool Agent Learning","created":"2024-01-19","cited_by_count":69},{"id":"2404.12387","title":"Reka Core, Flash, and Edge: A Series of Powerful Multimodal Language Models","created":"2024-04-18","cited_by_count":67},{"id":"2311.18775","title":"CoDi-2: In-Context, Interleaved, and Interactive Any-to-Any Generation","created":"2023-11-30","cited_by_count":63},{"id":"2302.00763","title":"Collaborating with language models for embodied reasoning","created":"2023-02-01","cited_by_count":61},{"id":"2504.16656","title":"Skywork R1V2: Multimodal Hybrid Reinforcement Learning for Reasoning","created":"2025-04-23","cited_by_count":49},{"id":"2403.13248","title":"Mora: Enabling Generalist Video Generation via A Multi-Agent Framework","created":"2024-03-20","cited_by_count":45},{"id":"2406.08407","title":"MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos","created":"2024-06-12","cited_by_count":43},{"id":"2309.10537","title":"FoleyGen: Visually-Guided Audio Generation","created":"2023-09-19","cited_by_count":40},{"id":"2408.11788","title":"DreamFactory: Pioneering Multi-Scene Long Video Generation with a Multi-Agent Framework","created":"2024-08-21","cited_by_count":35},{"id":"2502.11903","title":"MMRC: A Large-Scale Benchmark for Understanding Multimodal Large Language Model in Real-World Conversation","created":"2025-02-17","cited_by_count":29},{"id":"2405.09713","title":"SOK-Bench: A Situated Video Reasoning Benchmark with Aligned Open-World Knowledge","created":"2024-05-15","cited_by_count":25},{"id":"2312.01564","title":"APoLLo: Unified Adapter and Prompt Learning for Vision Language Models","created":"2023-12-04","cited_by_count":19},{"id":"2406.04673","title":"MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models","created":"2024-06-07","cited_by_count":19},{"id":"2505.24876","title":"Agent-X: Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic Tasks","created":"2025-05-30","cited_by_count":19},{"id":"2402.05889","title":"CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion","created":"2024-02-08","cited_by_count":17},{"id":"2306.15662","title":"Measured Albedo in the Wild: Filling the Gap in Intrinsics Evaluation","created":"2023-06-27","cited_by_count":16},{"id":"2308.12370","title":"AdVerb: Visually Guided Audio Dereverberation","created":"2023-08-23","cited_by_count":15},{"id":"2110.14862","title":"Audio-visual Representation Learning for Anomaly Events Detection in Crowds","created":"2021-10-28","cited_by_count":13},{"id":"2410.01731","title":"ComfyGen: Prompt-Adaptive Workflows for Text-to-Image Generation","created":"2024-10-02","cited_by_count":11},{"id":"2411.18983","title":"SPAgent: Adaptive Task Decomposition and Model Selection for General Video Generation and Editing","created":"2024-11-28","cited_by_count":11},{"id":"2406.10889","title":"VELOCITI: Benchmarking Video-Language Compositional Reasoning with Strict Entailment","created":"2024-06-16","cited_by_count":10},{"id":"2412.17295","title":"Friends-MMC: A Dataset for Multi-modal Multi-party Conversation Understanding","created":"2024-12-23","cited_by_count":9},{"id":"2503.23219","title":"Aurelia: Test-time Reasoning Distillation in Audio-Visual LLMs","created":"2025-03-29","cited_by_count":9},{"id":"2508.07470","title":"AURA: A Fine-Grained Benchmark and Decomposed Metric for Audio-Visual Reasoning","created":"2025-08-10","cited_by_count":8},{"id":"2403.11487","title":"Can LLMs Generate Human-Like Wayfinding Instructions? Towards Platform-Agnostic Embodied Instruction Synthesis","created":"2024-03-18","cited_by_count":6},{"id":"2505.14562","title":"Representation Learning for Semantic Alignment of Language, Audio, and Visual Modalities","created":"2025-05-20","cited_by_count":4},{"id":"2506.21080","title":"EgoAdapt: Adaptive Multisensory Distillation and Policy Learning for Efficient Egocentric Perception","created":"2025-06-26","cited_by_count":4},{"id":"2508.12257","title":"Structuring the Unstructured: A Systematic Review of Text-to-Structure Generation for Agentic AI with a Universal Evaluation Framework","created":"2025-08-17","cited_by_count":2}],"next_cursor":null}