{"total":69,"rows":[{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546,"area":null},{"id":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382,"area":null},{"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,"area":null},{"id":"2309.15112","title":"InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition","created":"2023-09-26","cited_by_count":297,"area":null},{"id":"2307.05222","title":"Emu: Generative Pretraining in Multimodality","created":"2023-07-11","cited_by_count":157,"area":null},{"id":"2306.05179","title":"M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models","created":"2023-06-08","cited_by_count":110,"area":null},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110,"area":null},{"id":"2404.07973","title":"Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models","created":"2024-04-11","cited_by_count":97,"area":null},{"id":"2411.04986","title":"The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities","created":"2024-11-07","cited_by_count":69,"area":null},{"id":"2305.14800","title":"Exploring Diverse In-Context Configurations for Image Captioning","created":"2023-05-24","cited_by_count":63,"area":null},{"id":"2405.08295","title":"SpeechVerse: A Large-scale Generalizable Audio Language Model","created":"2024-05-14","cited_by_count":63,"area":null},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58,"area":null},{"id":"2505.12540","title":"Harnessing the Universal Geometry of Embeddings","created":"2025-05-18","cited_by_count":55,"area":null},{"id":"2306.16410","title":"Towards Language Models That Can See: Computer Vision Through the LENS of Natural Language","created":"2023-06-28","cited_by_count":53,"area":null},{"id":"2504.07951","title":"Scaling Laws for Native Multimodal Models","created":"2025-04-10","cited_by_count":50,"area":null},{"id":"2310.12973","title":"Frozen Transformers in Language Models Are Effective Visual Encoder Layers","created":"2023-10-19","cited_by_count":39,"area":null},{"id":"2402.01763","title":"When Large Language Models Meet Vector Databases: A Survey","created":"2024-01-30","cited_by_count":39,"area":null},{"id":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35,"area":null},{"id":"2402.06475","title":"Large Language Models for Captioning and Retrieving Remote Sensing Images","created":"2024-02-09","cited_by_count":30,"area":null},{"id":"2403.08857","title":"DialogGen: Multi-modal Interactive Dialogue System for Multi-turn Text-to-Image Generation","created":"2024-03-13","cited_by_count":26,"area":null},{"id":"2403.17343","title":"Residual-based Language Models are Free Boosters for Biomedical Imaging","created":"2024-03-26","cited_by_count":24,"area":null},{"id":"2404.18624","title":"Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explanations?","created":"2024-04-29","cited_by_count":24,"area":null},{"id":"2309.08637","title":"TextBind: Multi-turn Interleaved Multimodal Instruction-following in the Wild","created":"2023-09-14","cited_by_count":22,"area":null},{"id":"2311.09580","title":"MMoE: Enhancing Multimodal Models with Mixtures of Multimodal Interaction Experts","created":"2023-11-16","cited_by_count":21,"area":null},{"id":"2312.03584","title":"Context Diffusion: In-Context Aware Image Generation","created":"2023-12-06","cited_by_count":21,"area":null},{"id":"2405.17927","title":"The Evolution of Multimodal Model Architectures","created":"2024-05-28","cited_by_count":21,"area":null},{"id":"2407.03418","title":"HEMM: Holistic Evaluation of Multimodal Foundation Models","created":"2024-07-03","cited_by_count":21,"area":null},{"id":"2403.13499","title":"Improved Baselines for Data-efficient Perceptual Augmentation of LLMs","created":"2024-03-20","cited_by_count":18,"area":null},{"id":"2507.19599","title":"Object-centric Video Question Answering with Visual Grounding and Referring","created":"2025-07-25","cited_by_count":13,"area":null},{"id":"2310.17050","title":"Exploring Question Decomposition for Zero-Shot VQA","created":"2023-10-25","cited_by_count":12,"area":null},{"id":"2402.18695","title":"Grounding Language Models for Visual Entity Recognition","created":"2024-02-28","cited_by_count":12,"area":null},{"id":"2409.16667","title":"A Character-Centric Creative Story Generation via Imagination","created":"2024-09-25","cited_by_count":12,"area":null},{"id":"2404.09632","title":"Bridging Vision and Language Spaces with Assignment Prediction","created":"2024-04-15","cited_by_count":11,"area":null},{"id":"2404.15790","title":"Leveraging Large Language Models for Multimodal Search","created":"2024-04-24","cited_by_count":11,"area":null},{"id":"2502.08279","title":"What Is That Talk About? A Video-to-Text Summarization Dataset for Scientific Presentations","created":"2025-02-12","cited_by_count":11,"area":null},{"id":"2510.05184","title":"Representation Potentials of Foundation Models for Multimodal Alignment: A Survey","created":"2025-10-05","cited_by_count":11,"area":null},{"id":"2402.10977","title":"Generative AI and Process Systems Engineering: The Next Frontier","created":"2024-02-15","cited_by_count":9,"area":null},{"id":"2408.05926","title":"BI-MDRG: Bridging Image History in Multimodal Dialogue Response Generation","created":"2024-08-12","cited_by_count":8,"area":null},{"id":"2312.04552","title":"Generating Illustrated Instructions","created":"2023-12-07","cited_by_count":7,"area":null},{"id":"2405.19333","title":"Multi-Modal Generative Embedding Model","created":"2024-05-29","cited_by_count":7,"area":null},{"id":"2503.09402","title":"VLog: Video-Language Models by Generative Retrieval of Narration Vocabulary","created":"2025-03-12","cited_by_count":7,"area":null},{"id":"2410.18715","title":"ChatSearch: a Dataset and a Generative Retrieval Model for General Conversational Image Retrieval","created":"2024-10-24","cited_by_count":6,"area":null},{"id":"2408.14547","title":"Revisiting Image Captioning Training Paradigm via Direct CLIP-based Optimization","created":"2024-08-26","cited_by_count":5,"area":null},{"id":"2505.19707","title":"MLLM-Guided VLM Fine-Tuning with Joint Inference for Zero-Shot Composed Image Retrieval","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2312.07532","title":"Interfacing Foundation Models' Embeddings","created":"2023-12-12","cited_by_count":4,"area":null},{"id":"2604.04496","title":"The Indra Representation Hypothesis for Multimodal Alignment","created":"2026-04-06","cited_by_count":4,"area":null},{"id":"2403.06935","title":"Naming, Describing, and Quantifying Visual Objects in Humans and LLMs","created":"2024-03-11","cited_by_count":3,"area":null},{"id":"2403.15209","title":"MSCoTDet: Language-driven Multi-modal Fusion for Improved Multispectral Pedestrian Detection","created":"2024-03-22","cited_by_count":3,"area":null},{"id":"2407.11449","title":"Controllable Contextualized Image Captioning: Directing the Visual Narrative through User-Defined Highlights","created":"2024-07-16","cited_by_count":3,"area":null},{"id":"2408.14153","title":"Explaining Caption-Image Interactions in CLIP Models with Second-Order Attributions","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2404.13530","title":"Listen Then See: Video Alignment with Speaker Attention","created":"2024-04-21","cited_by_count":2,"area":null},{"id":"2405.18304","title":"Multi-modal Generation via Cross-Modal In-Context Learning","created":"2024-05-28","cited_by_count":2,"area":null},{"id":"2502.12799","title":"Towards Text-Image Interleaved Retrieval","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2506.02308","title":"MINT: Multimodal Instruction Tuning with Multimodal Interaction Grouping","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2405.02933","title":"Relay Decoding: Concatenating Large Language Models for Machine Translation","created":"2024-05-05","cited_by_count":1,"area":null},{"id":"2407.03615","title":"Visualizing Dialogues: Enhancing Image Selection through Dialogue Understanding with Large Language Models","created":"2024-07-04","cited_by_count":1,"area":null},{"id":"2407.12833","title":"ESQA: Event Sequences Question Answering","created":"2024-07-03","cited_by_count":1,"area":null},{"id":"2408.03001","title":"One Framework to Rule Them All: Unifying Multimodal Tasks with LLM Neural-Tuning","created":"2024-08-06","cited_by_count":1,"area":null},{"id":"2509.04606","title":"Sample-efficient Integration of New Modalities into Large Language Models","created":"2025-09-04","cited_by_count":1,"area":null},{"id":"2303.05983","title":"Accountable Textual-Visual Chat Learns to Reject Human Instructions in Image Re-creation","created":"2023-03-10","cited_by_count":0,"area":null},{"id":"2405.16728","title":"Towards Multi-Task Multi-Modal Models: A Video Generative Perspective","created":"2024-05-26","cited_by_count":0,"area":null},{"id":"2406.06048","title":"Robust Latent Representation Tuning for Image-text Classification","created":"2024-06-10","cited_by_count":0,"area":null},{"id":"2406.18305","title":"S3: A Simple Strong Sample-effective Multimodal Dialog System","created":"2024-06-26","cited_by_count":0,"area":null},{"id":"2502.18047","title":"Progressive Local Alignment for Medical Multimodal Pre-training","created":"2025-02-25","cited_by_count":0,"area":null},{"id":"2503.02063","title":"V$^2$Dial: Unification of Video and Visual Dialog via Multimodal Experts","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2507.12739","title":"Transformer-based Spatial Grounding: A Comprehensive Survey","created":"2025-07-17","cited_by_count":0,"area":null},{"id":"2608.18138","title":"Language Models for Portuguese: A Systematic Mapping Study","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2610.05897","title":"Fitting Vision Adapters at Frontier Scales","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.18638","title":"To Align or Not To Align: Check Your COMPASS Before You Train","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}