{"list":"other","total":77,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"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":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919},{"id":"2305.10355","title":"Evaluating Object Hallucination in Large Vision-Language Models","created":"2023-05-17","cited_by_count":1729},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"1802.08218","title":"VizWiz Grand Challenge: Answering Visual Questions from Blind People","created":"2018-02-22","cited_by_count":858},{"id":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798},{"id":"2301.12652","title":"REPLUG: Retrieval-Augmented Black-Box Language Models","created":"2023-01-30","cited_by_count":792},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"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":"2308.01390","title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","created":"2023-08-02","cited_by_count":565},{"id":"2204.03162","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","created":"2022-04-07","cited_by_count":529},{"id":"1705.02364","title":"Supervised Learning of Universal Sentence Representations from Natural Language Inference Data","created":"2017-05-05","cited_by_count":432},{"id":"2404.18930","title":"Hallucination of Multimodal Large Language Models: A Survey","created":"2024-04-29","cited_by_count":388},{"id":"2310.08319","title":"Fine-Tuning LLaMA for Multi-Stage Text Retrieval","created":"2023-10-12","cited_by_count":272},{"id":"1703.01541","title":"Soft-DTW: a Differentiable Loss Function for Time-Series","created":"2017-03-05","cited_by_count":271},{"id":"2309.16671","title":"Demystifying CLIP Data","created":"2023-09-28","cited_by_count":270},{"id":"2309.17425","title":"Data Filtering Networks","created":"2023-09-29","cited_by_count":250},{"id":"2402.09906","title":"Generative Representational Instruction Tuning","created":"2024-02-15","cited_by_count":233},{"id":"2304.06939","title":"Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Text","created":"2023-04-14","cited_by_count":208},{"id":"2202.08904","title":"SGPT: GPT Sentence Embeddings for Semantic Search","created":"2022-02-17","cited_by_count":204},{"id":"2102.10772","title":"UniT: Multimodal Multitask Learning with a Unified Transformer","created":"2021-02-22","cited_by_count":195},{"id":"1606.05433","title":"FVQA: Fact-based Visual Question Answering","created":"2016-06-17","cited_by_count":181},{"id":"1604.03968","title":"Visual Storytelling","created":"2016-04-13","cited_by_count":176},{"id":"2311.17136","title":"UniIR: Training and Benchmarking Universal Multimodal Information Retrievers","created":"2023-11-28","cited_by_count":166},{"id":"2501.03230","title":"Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition","created":"2024-05-07","cited_by_count":153},{"id":"2201.07520","title":"CM3: A Causal Masked Multimodal Model of the Internet","created":"2022-01-19","cited_by_count":142},{"id":"2311.13614","title":"HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data","created":"2023-11-22","cited_by_count":126},{"id":"2211.12561","title":"Retrieval-Augmented Multimodal Language Modeling","created":"2022-11-22","cited_by_count":125},{"id":"2401.10208","title":"MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer","created":"2024-01-18","cited_by_count":80},{"id":"2312.15503","title":"Llama2Vec: Unsupervised Adaptation of Large Language Models for Dense Retrieval","created":"2023-12-24","cited_by_count":78},{"id":"2312.17240","title":"LISA++: An Improved Baseline for Reasoning Segmentation with Large Language Model","created":"2023-12-28","cited_by_count":71},{"id":"2208.02515","title":"Fine-Grained Semantically Aligned Vision-Language Pre-Training","created":"2022-08-04","cited_by_count":68},{"id":"2304.04487","title":"Inference with Reference: Lossless Acceleration of Large Language Models","created":"2023-04-10","cited_by_count":65},{"id":"2410.08261","title":"Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis","created":"2024-10-10","cited_by_count":56},{"id":"2309.17133","title":"Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering","created":"2023-09-29","cited_by_count":51},{"id":"2412.19806","title":"Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing","created":"2024-10-08","cited_by_count":49},{"id":"2406.05127","title":"Towards Semantic Equivalence of Tokenization in Multimodal LLM","created":"2024-06-07","cited_by_count":45},{"id":"2305.12223","title":"What Makes for Good Visual Tokenizers for Large Language Models?","created":"2023-05-20","cited_by_count":42},{"id":"2402.08327","title":"PreFLMR: Scaling Up Fine-Grained Late-Interaction Multi-modal Retrievers","created":"2024-02-13","cited_by_count":42},{"id":"2404.18202","title":"WorldGPT: Empowering LLM as Multimodal World Model","created":"2024-04-28","cited_by_count":42},{"id":"2302.04858","title":"Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning","created":"2023-02-09","cited_by_count":41},{"id":"2107.05348","title":"Zero-shot Visual Question Answering using Knowledge Graph","created":"2021-07-12","cited_by_count":37},{"id":"2303.13233","title":"Visually-Prompted Language Model for Fine-Grained Scene Graph Generation in an Open World","created":"2023-03-23","cited_by_count":35},{"id":"2406.19255","title":"Enhancing Video-Language Representations with Structural Spatio-Temporal Alignment","created":"2024-06-27","cited_by_count":32},{"id":"2403.13805","title":"RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition","created":"2024-03-20","cited_by_count":24},{"id":"2210.15718","title":"QUILL: Query Intent with Large Language Models using Retrieval Augmentation and Multi-stage Distillation","created":"2022-10-27","cited_by_count":21},{"id":"2303.06571","title":"Gradient-Regulated Meta-Prompt Learning for Generalizable Vision-Language Models","created":"2023-03-12","cited_by_count":21},{"id":"2301.09071","title":"Variational Cross-Graph Reasoning and Adaptive Structured Semantics Learning for Compositional Temporal Grounding","created":"2023-01-22","cited_by_count":19},{"id":"2409.19872","title":"Towards Unified Multimodal Editing with Enhanced Knowledge Collaboration","created":"2024-09-30","cited_by_count":18},{"id":"2404.04163","title":"Dwell in the Beginning: How Language Models Embed Long Documents for Dense Retrieval","created":"2024-04-05","cited_by_count":13},{"id":"2404.12866","title":"How Does the Textual Information Affect the Retrieval of Multimodal In-Context Learning?","created":"2024-04-19","cited_by_count":13},{"id":"2404.15790","title":"Leveraging Large Language Models for Multimodal Search","created":"2024-04-24","cited_by_count":11},{"id":"2311.12890","title":"De-fine: Decomposing and Refining Visual Programs with Auto-Feedback","created":"2023-11-21","cited_by_count":10},{"id":"2402.02168","title":"Enhancing Cross-domain Link Prediction via Evolution Process Modeling","created":"2024-02-03","cited_by_count":7},{"id":"2207.04211","title":"BOSS: Bottom-up Cross-modal Semantic Composition with Hybrid Counterfactual Training for Robust Content-based Image Retrieval","created":"2022-07-09","cited_by_count":4},{"id":"2311.17072","title":"IG Captioner: Information Gain Captioners are Strong Zero-shot Classifiers","created":"2023-11-27","cited_by_count":2},{"id":"1809.03313","title":"A Global Alignment Kernel based Approach for Group-level Happiness Intensity Estimation","created":"2018-09-03","cited_by_count":1}],"next_cursor":null}