{"list":"other","total":103,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"1306.0895","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","created":"2013-06-04","cited_by_count":2316},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006},{"id":"2305.10355","title":"Evaluating Object Hallucination in Large Vision-Language Models","created":"2023-05-17","cited_by_count":1729},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"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":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"2306.15195","title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","created":"2023-06-27","cited_by_count":906},{"id":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"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":"2308.03281","title":"Towards General Text Embeddings with Multi-stage Contrastive Learning","created":"2023-08-07","cited_by_count":723},{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708},{"id":"2302.00083","title":"In-Context Retrieval-Augmented Language Models","created":"2023-01-31","cited_by_count":702},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"2310.09478","title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","created":"2023-10-14","cited_by_count":625},{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615},{"id":"2407.07895","title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","created":"2024-07-10","cited_by_count":584},{"id":"2401.01614","title":"GPT-4V(ision) is a Generalist Web Agent, if Grounded","created":"2024-01-03","cited_by_count":563},{"id":"2306.14565","title":"Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning","created":"2023-06-26","cited_by_count":445},{"id":"2312.13771","title":"AppAgent: Multimodal Agents as Smartphone Users","created":"2023-12-21","cited_by_count":415},{"id":"2312.02051","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","created":"2023-12-04","cited_by_count":406},{"id":"2402.00253","title":"A Survey on Hallucination in Large Vision-Language Models","created":"2024-02-01","cited_by_count":357},{"id":"2106.13043","title":"AudioCLIP: Extending CLIP to Image, Text and Audio","created":"2021-06-24","cited_by_count":339},{"id":"2306.16527","title":"OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents","created":"2023-06-21","cited_by_count":316},{"id":"2310.00754","title":"Analyzing and Mitigating Object Hallucination in Large Vision-Language Models","created":"2023-10-01","cited_by_count":316},{"id":"2307.03601","title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest","created":"2023-07-07","cited_by_count":302},{"id":"2306.05425","title":"MIMIC-IT: Multi-Modal In-Context Instruction Tuning","created":"2023-06-08","cited_by_count":267},{"id":"2304.12995","title":"AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head","created":"2023-04-25","cited_by_count":265},{"id":"2308.06394","title":"Detecting and Preventing Hallucinations in Large Vision Language Models","created":"2023-08-11","cited_by_count":256},{"id":"2206.01670","title":"Egocentric Video-Language Pretraining","created":"2022-06-03","cited_by_count":232},{"id":"2402.12226","title":"AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling","created":"2024-02-19","cited_by_count":217},{"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},{"id":"2201.02639","title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","created":"2022-01-07","cited_by_count":184},{"id":"2408.05211","title":"VITA: Towards Open-Source Interactive Omni Multimodal LLM","created":"2024-08-09","cited_by_count":173},{"id":"2309.07915","title":"MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning","created":"2023-09-14","cited_by_count":172},{"id":"2108.04106","title":"Noisy Channel Language Model Prompting for Few-Shot Text Classification","created":"2021-08-09","cited_by_count":165},{"id":"2402.17553","title":"OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web","created":"2024-02-27","cited_by_count":157},{"id":"2205.10782","title":"Instruction Induction: From Few Examples to Natural Language Task Descriptions","created":"2022-05-22","cited_by_count":152},{"id":"2207.05042","title":"Audio-Visual Segmentation","created":"2022-07-11","cited_by_count":151},{"id":"2303.08137","title":"LayoutDM: Discrete Diffusion Model for Controllable Layout Generation","created":"2023-03-14","cited_by_count":143},{"id":"2309.03905","title":"ImageBind-LLM: Multi-modality Instruction Tuning","created":"2023-09-07","cited_by_count":142},{"id":"2305.16938","title":"Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation","created":"2023-05-26","cited_by_count":136},{"id":"2307.05463","title":"EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone","created":"2023-07-11","cited_by_count":130},{"id":"2403.09029","title":"Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Dataset","created":"2024-03-14","cited_by_count":129},{"id":"1809.00013","title":"Gromov-Wasserstein Alignment of Word Embedding Spaces","created":"2018-08-31","cited_by_count":122},{"id":"2111.12085","title":"UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling","created":"2021-11-23","cited_by_count":122},{"id":"2402.06332","title":"InternLM-Math: Open Math Large Language Models Toward Verifiable Reasoning","created":"2024-02-09","cited_by_count":119},{"id":"2307.08581","title":"BuboGPT: Enabling Visual Grounding in Multi-Modal LLMs","created":"2023-07-17","cited_by_count":114},{"id":"2402.15116","title":"Large Multimodal Agents: A Survey","created":"2024-02-23","cited_by_count":105},{"id":"2406.15704","title":"video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models","created":"2024-06-22","cited_by_count":102},{"id":"2108.01249","title":"CanvasVAE: Learning to Generate Vector Graphic Documents","created":"2021-08-03","cited_by_count":95},{"id":"2404.05225","title":"LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding","created":"2024-04-08","cited_by_count":95},{"id":"2309.16058","title":"AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model","created":"2023-09-27","cited_by_count":93},{"id":"2212.06713","title":"Structured Prompting: Scaling In-Context Learning to 1,000 Examples","created":"2022-12-13","cited_by_count":81},{"id":"2310.05338","title":"Negative Object Presence Evaluation (NOPE) to Measure Object Hallucination in Vision-Language Models","created":"2023-10-09","cited_by_count":80},{"id":"2311.18799","title":"X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning","created":"2023-11-30","cited_by_count":80},{"id":"2310.08588","title":"Octopus: Embodied Vision-Language Programmer from Environmental Feedback","created":"2023-10-12","cited_by_count":73},{"id":"2307.01146","title":"AVSegFormer: Audio-Visual Segmentation with Transformer","created":"2023-07-03","cited_by_count":68},{"id":"2305.16103","title":"ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst","created":"2023-05-25","cited_by_count":66},{"id":"2405.13872","title":"Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models","created":"2024-05-22","cited_by_count":65},{"id":"1805.11897","title":"Differential Properties of Sinkhorn Approximation for Learning with Wasserstein Distance","created":"2018-05-30","cited_by_count":56},{"id":"2312.12423","title":"Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model","created":"2023-12-19","cited_by_count":53},{"id":"2403.04640","title":"CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2024-03-07","cited_by_count":53},{"id":"2311.13435","title":"PG-Video-LLaVA: Pixel Grounding Large Video-Language Models","created":"2023-11-22","cited_by_count":51},{"id":"2311.06495","title":"LayoutPrompter: Awaken the Design Ability of Large Language Models","created":"2023-11-11","cited_by_count":48},{"id":"2311.17435","title":"MM-Narrator: Narrating Long-form Videos with Multimodal In-Context Learning","created":"2023-11-29","cited_by_count":46},{"id":"2311.16974","title":"COLE: A Hierarchical Generation Framework for Multi-Layered and Editable Graphic Design","created":"2023-11-28","cited_by_count":43},{"id":"2406.02884","title":"PosterLLaVa: Constructing a Unified Multi-modal Layout Generator with LLM","created":"2024-06-05","cited_by_count":41},{"id":"2403.07407","title":"In-context learning enables multimodal large language models to classify cancer pathology images","created":"2024-03-12","cited_by_count":38},{"id":"2406.08232","title":"OpenCOLE: Towards Reproducible Automatic Graphic Design Generation","created":"2024-06-12","cited_by_count":37},{"id":"2303.18248","title":"Towards Flexible Multi-modal Document Models","created":"2023-03-31","cited_by_count":31},{"id":"2307.14335","title":"WavJourney: Compositional Audio Creation with Large Language Models","created":"2023-07-26","cited_by_count":27},{"id":"2407.01851","title":"Meerkat: Audio-Visual Large Language Model for Grounding in Space and Time","created":"2024-07-01","cited_by_count":26},{"id":"2403.18187","title":"LayoutFlow: Flow Matching for Layout Generation","created":"2024-03-27","cited_by_count":21},{"id":"2210.04135","title":"VoLTA: Vision-Language Transformer with Weakly-Supervised Local-Feature Alignment","created":"2022-10-09","cited_by_count":20},{"id":"2303.03755","title":"DLT: Conditioned layout generation with Joint Discrete-Continuous Diffusion Layout Transformer","created":"2023-03-07","cited_by_count":20},{"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":"2501.02135","title":"AVTrustBench: Assessing and Enhancing Reliability and Robustness in Audio-Visual LLMs","created":"2025-01-03","cited_by_count":19},{"id":"2309.04790","title":"MMHQA-ICL: Multimodal In-context Learning for Hybrid Question Answering over Text, Tables and Images","created":"2023-09-09","cited_by_count":18},{"id":"2310.12404","title":"Loop Copilot: Conducting AI Ensembles for Music Generation and Iterative Editing","created":"2023-10-19","cited_by_count":15},{"id":"2410.08885","title":"Can GPTs Evaluate Graphic Design Based on Design Principles?","created":"2024-10-11","cited_by_count":14},{"id":"2312.15011","title":"Gemini vs GPT-4V: A Preliminary Comparison and Combination of Vision-Language Models Through Qualitative Cases","created":"2023-12-22","cited_by_count":12},{"id":"2506.07016","title":"MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks","created":"2025-06-08","cited_by_count":12},{"id":"2403.06252","title":"Demystifying Tacit Knowledge in Graphic Design: Characteristics, Instances, Approaches, and Guidelines","created":"2024-03-10","cited_by_count":10},{"id":"2411.11909","title":"SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization","created":"2024-11-17","cited_by_count":10},{"id":"2503.23219","title":"Aurelia: Test-time Reasoning Distillation in Audio-Visual LLMs","created":"2025-03-29","cited_by_count":9}],"next_cursor":"100"}