{"list":"other","total":96,"rows":[{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"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":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","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":"2310.11511","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","created":"2023-10-17","cited_by_count":1839},{"id":"2310.02255","title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","created":"2023-10-03","cited_by_count":1614},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2408.12528","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","created":"2024-08-22","cited_by_count":752},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"2308.03281","title":"Towards General Text Embeddings with Multi-stage Contrastive Learning","created":"2023-08-07","cited_by_count":723},{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680},{"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":"2403.14624","title":"MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?","created":"2024-03-21","cited_by_count":586},{"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":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542},{"id":"2305.06983","title":"Active Retrieval Augmented Generation","created":"2023-05-11","cited_by_count":516},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"2306.06546","title":"High-Fidelity Audio Compression with Improved RVQGAN","created":"2023-06-11","cited_by_count":431},{"id":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421},{"id":"2406.04325","title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","created":"2024-06-06","cited_by_count":388},{"id":"2402.19473","title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","created":"2024-02-29","cited_by_count":354},{"id":"2403.10517","title":"VideoAgent: Long-form Video Understanding with Large Language Model as Agent","created":"2024-03-15","cited_by_count":332},{"id":"2305.13786","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","created":"2023-05-23","cited_by_count":314},{"id":"1512.02902","title":"MovieQA: Understanding Stories in Movies through Question-Answering","created":"2015-12-09","cited_by_count":304},{"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":"2405.19209","title":"VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos","created":"2024-05-29","cited_by_count":251},{"id":"2012.00451","title":"Just Ask: Learning to Answer Questions from Millions of Narrated Videos","created":"2020-12-01","cited_by_count":248},{"id":"2410.10594","title":"VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents","created":"2024-10-14","cited_by_count":245},{"id":"2210.02928","title":"MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text","created":"2022-10-06","cited_by_count":220},{"id":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213},{"id":"2203.14072","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2022-03-26","cited_by_count":191},{"id":"2408.05211","title":"VITA: Towards Open-Source Interactive Omni Multimodal LLM","created":"2024-08-09","cited_by_count":173},{"id":"2305.18500","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","created":"2023-05-29","cited_by_count":169},{"id":"2406.08085","title":"Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams","created":"2024-06-12","cited_by_count":169},{"id":"1811.00347","title":"How2: A Large-scale Dataset for Multimodal Language Understanding","created":"2018-11-01","cited_by_count":138},{"id":"2411.13093","title":"Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension","created":"2024-11-20","cited_by_count":138},{"id":"2307.05463","title":"EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone","created":"2023-07-11","cited_by_count":130},{"id":"2103.16002","title":"AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning","created":"2021-03-30","cited_by_count":120},{"id":"2405.08813","title":"CinePile: A Long Video Question Answering Dataset and Benchmark","created":"2024-05-14","cited_by_count":114},{"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":"2405.18541","title":"Low-Rank Few-Shot Adaptation of Vision-Language Models","created":"2024-05-28","cited_by_count":104},{"id":"2502.04144","title":"HD-EPIC: A Highly-Detailed Egocentric Video Dataset","created":"2025-02-06","cited_by_count":104},{"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":"2210.03809","title":"Retrieval Augmented Visual Question Answering with Outside Knowledge","created":"2022-10-07","cited_by_count":94},{"id":"2203.01225","title":"Video Question Answering: Datasets, Algorithms and Challenges","created":"2022-03-02","cited_by_count":84},{"id":"2407.01219","title":"Searching for Best Practices in Retrieval-Augmented Generation","created":"2024-07-01","cited_by_count":83},{"id":"2012.11583","title":"Semantic Audio-Visual Navigation","created":"2020-12-21","cited_by_count":82},{"id":"2404.10981","title":"A Survey on Retrieval-Augmented Text Generation for Large Language Models","created":"2024-04-17","cited_by_count":77},{"id":"2502.01549","title":"VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos","created":"2025-02-03","cited_by_count":77},{"id":"2407.13193","title":"Retrieval-Augmented Generation for Natural Language Processing: A Survey","created":"2024-07-18","cited_by_count":71},{"id":"2404.07214","title":"Exploring the Frontier of Vision-Language Models: A Survey of Current Methodologies and Future Directions","created":"2024-02-20","cited_by_count":68},{"id":"2311.18775","title":"CoDi-2: In-Context, Interleaved, and Interactive Any-to-Any Generation","created":"2023-11-30","cited_by_count":63},{"id":"2407.05131","title":"RULE: Reliable Multimodal RAG for Factuality in Medical Vision Language Models","created":"2024-07-06","cited_by_count":60},{"id":"2310.05473","title":"Sentence-level Prompts Benefit Composed Image Retrieval","created":"2023-10-09","cited_by_count":59},{"id":"2504.09795","title":"VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents","created":"2025-04-14","cited_by_count":59},{"id":"2410.18325","title":"AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models","created":"2024-10-23","cited_by_count":56},{"id":"2407.13766","title":"Visual Haystacks: A Vision-Centric Needle-In-A-Haystack Benchmark","created":"2024-07-18","cited_by_count":55},{"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":"2411.19772","title":"LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos","created":"2024-11-29","cited_by_count":51},{"id":"2303.12930","title":"Dense-Localizing Audio-Visual Events in Untrimmed Videos: A Large-Scale Benchmark and Baseline","created":"2023-03-22","cited_by_count":46},{"id":"2309.10537","title":"FoleyGen: Visually-Guided Audio Generation","created":"2023-09-19","cited_by_count":40},{"id":"2305.15225","title":"SAIL: Search-Augmented Instruction Learning","created":"2023-05-24","cited_by_count":33},{"id":"2407.15268","title":"Fact-Aware Multimodal Retrieval Augmentation for Accurate Medical Radiology Report Generation","created":"2024-07-21","cited_by_count":23},{"id":"2210.04135","title":"VoLTA: Vision-Language Transformer with Weakly-Supervised Local-Feature Alignment","created":"2022-10-09","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":"2503.13068","title":"Crab: A Unified Audio-Visual Scene Understanding Model with Explicit Cooperation","created":"2025-03-17","cited_by_count":18},{"id":"2402.05889","title":"CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion","created":"2024-02-08","cited_by_count":17},{"id":"2411.16740","title":"Document Haystacks: Vision-Language Reasoning Over Piles of 1000+ Documents","created":"2024-11-23","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":"2502.16636","title":"Visual-RAG: Benchmarking Text-to-Image Retrieval Augmented Generation for Visual Knowledge Intensive Queries","created":"2025-02-23","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":"2312.12273","title":"VQA4CIR: Boosting Composed Image Retrieval with Visual Question Answering","created":"2023-12-19","cited_by_count":11},{"id":"1911.03083","title":"Are we asking the right questions in MovieQA?","created":"2019-11-08","cited_by_count":10},{"id":"2402.15414","title":"Does Combining Parameter-efficient Modules Improve Few-shot Transfer Accuracy?","created":"2024-02-23","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":"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":"2407.02389","title":"SafaRi:Adaptive Sequence Transformer for Weakly Supervised Referring Expression Segmentation","created":"2024-07-02","cited_by_count":6},{"id":"2504.05040","title":"InstructionBench: An Instructional Video Understanding Benchmark","created":"2025-04-07","cited_by_count":5},{"id":"2411.16213","title":"SAVEn-Vid: Synergistic Audio-Visual Integration for Enhanced Understanding in Long Video Context","created":"2024-11-25","cited_by_count":4},{"id":"2505.14562","title":"Representation Learning for Semantic Alignment of Language, Audio, and Visual Modalities","created":"2025-05-20","cited_by_count":4}],"next_cursor":null}