{"total":60,"rows":[{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917,"area":null},{"id":"2408.12528","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","created":"2024-08-22","cited_by_count":752,"area":null},{"id":"2412.14164","title":"MetaMorph: Multimodal Understanding and Generation via Instruction Tuning","created":"2024-12-18","cited_by_count":206,"area":null},{"id":"2502.20321","title":"UniTok: A Unified Tokenizer for Visual Generation and Understanding","created":"2025-02-27","cited_by_count":153,"area":null},{"id":"2409.20537","title":"Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformers","created":"2024-09-30","cited_by_count":148,"area":null},{"id":"2407.15841","title":"SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models","created":"2024-07-22","cited_by_count":125,"area":null},{"id":"2411.14402","title":"Multimodal Autoregressive Pre-training of Large Vision Encoders","created":"2024-11-21","cited_by_count":109,"area":null},{"id":"2409.00088","title":"On-Device Language Models: A Comprehensive Review","created":"2024-08-26","cited_by_count":104,"area":null},{"id":"2405.18415","title":"Why are Visually-Grounded Language Models Bad at Image Classification?","created":"2024-05-28","cited_by_count":102,"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":"2406.08418","title":"OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text","created":"2024-06-12","cited_by_count":59,"area":null},{"id":"2510.15870","title":"OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM","created":"2025-10-17","cited_by_count":59,"area":null},{"id":"2409.13689","title":"Temporally Aligned Audio for Video with Autoregression","created":"2024-09-20","cited_by_count":52,"area":null},{"id":"2410.18967","title":"Ferret-UI 2: Mastering Universal User Interface Understanding Across Platforms","created":"2024-10-24","cited_by_count":51,"area":null},{"id":"2404.01266","title":"IsoBench: Benchmarking Multimodal Foundation Models on Isomorphic Representations","created":"2024-04-01","cited_by_count":38,"area":null},{"id":"2403.12844","title":"MELTing point: Mobile Evaluation of Language Transformers","created":"2024-03-19","cited_by_count":36,"area":null},{"id":"2405.16411","title":"Training Tensor Attention Efficiently: From Cubic to Almost Linear Time","created":"2024-05-26","cited_by_count":30,"area":null},{"id":"2503.18943","title":"SlowFast-LLaVA-1.5: A Family of Token-Efficient Video Large Language Models for Long-Form Video Understanding","created":"2025-03-24","cited_by_count":30,"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":"2502.13759","title":"Geolocation with Real Human Gameplay Data: A Large-Scale Dataset and Human-Like Reasoning Framework","created":"2025-02-19","cited_by_count":24,"area":null},{"id":"2405.17927","title":"The Evolution of Multimodal Model Architectures","created":"2024-05-28","cited_by_count":21,"area":null},{"id":"2503.08507","title":"Referring to Any Person","created":"2025-03-11","cited_by_count":21,"area":null},{"id":"2407.12929","title":"The 2024 Foundation Model Transparency Index","created":"2024-07-17","cited_by_count":19,"area":null},{"id":"2502.18778","title":"M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performance","created":"2025-02-26","cited_by_count":19,"area":null},{"id":"2409.14713","title":"Phantom of Latent for Large Language and Vision Models","created":"2024-09-23","cited_by_count":17,"area":null},{"id":"2404.01331","title":"LLaVA-Gemma: Accelerating Multimodal Foundation Models with a Compact Language Model","created":"2024-03-29","cited_by_count":14,"area":null},{"id":"2406.04496","title":"Time Sensitive Knowledge Editing through Efficient Finetuning","created":"2024-06-06","cited_by_count":14,"area":null},{"id":"2406.12246","title":"TroL: Traversal of Layers for Large Language and Vision Models","created":"2024-06-18","cited_by_count":14,"area":null},{"id":"2406.13193","title":"PRESTO: Progressive Pretraining Enhances Synthetic Chemistry Outcomes","created":"2024-06-19","cited_by_count":14,"area":null},{"id":"2410.02740","title":"Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models","created":"2024-10-03","cited_by_count":14,"area":null},{"id":"2412.17316","title":"RoPE Attention Can Be Trained in Almost Linear Time","created":"2024-12-23","cited_by_count":13,"area":null},{"id":"2409.04095","title":"UNIT: Unifying Image and Text Recognition in One Vision Encoder","created":"2024-09-06","cited_by_count":12,"area":null},{"id":"2406.16746","title":"The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources","created":"2024-06-24","cited_by_count":11,"area":null},{"id":"2410.15453","title":"CROPE: Evaluating In-Context Adaptation of Vision and Language Models to Culture-Specific Concepts","created":"2024-10-20","cited_by_count":11,"area":null},{"id":"2405.13985","title":"LookHere: Vision Transformers with Directed Attention Generalize and Extrapolate","created":"2024-05-22","cited_by_count":10,"area":null},{"id":"2510.02423","title":"RefineShot: Rethinking Cinematography Understanding with Foundational Skill Evaluation","created":"2025-10-02","cited_by_count":10,"area":null},{"id":"2408.14811","title":"Brain-inspired Artificial Intelligence: A Comprehensive Review","created":"2024-08-27","cited_by_count":9,"area":null},{"id":"2410.15573","title":"OpenMU: Your Swiss Army Knife for Music Understanding","created":"2024-10-21","cited_by_count":9,"area":null},{"id":"2504.16030","title":"LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale","created":"2025-04-22","cited_by_count":9,"area":null},{"id":"2505.11892","title":"Fast RoPE Attention: Combining the Polynomial Method and Fast Fourier Transform","created":"2025-05-17","cited_by_count":9,"area":null},{"id":"2406.14150","title":"Multi-modal Transfer Learning between Biological Foundation Models","created":"2024-06-20","cited_by_count":7,"area":null},{"id":"2412.18609","title":"Video-Panda: Parameter-efficient Alignment for Encoder-free Video-Language Models","created":"2024-12-24","cited_by_count":7,"area":null},{"id":"2506.07643","title":"Synthetic Visual Genome","created":"2025-06-09","cited_by_count":6,"area":null},{"id":"2504.08368","title":"FocalLens: Instruction Tuning Enables Zero-Shot Conditional Image Representations","created":"2025-04-11","cited_by_count":4,"area":null},{"id":"2408.04680","title":"Dynamic Fog Computing for Enhanced LLM Execution in Medical Applications","created":"2024-08-08","cited_by_count":3,"area":null},{"id":"2412.18224","title":"Expand VSR Benchmark for VLLM to Expertize in Spatial Rules","created":"2024-12-24","cited_by_count":3,"area":null},{"id":"2405.03702","title":"Leafy Spurge Dataset: Real-world Weed Classification Within Aerial Drone Imagery","created":"2024-05-02","cited_by_count":2,"area":null},{"id":"2410.17779","title":"ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning","created":"2024-10-23","cited_by_count":2,"area":null},{"id":"2403.10171","title":"AUTONODE: A Neuro-Graphic Self-Learnable Engine for Cognitive GUI Automation","created":"2024-03-15","cited_by_count":1,"area":null},{"id":"2410.04751","title":"Intriguing Properties of Large Language and Vision Models","created":"2024-10-07","cited_by_count":1,"area":null},{"id":"2410.07880","title":"Unsupervised Data Validation Methods for Efficient Model Training","created":"2024-10-10","cited_by_count":1,"area":null},{"id":"2502.10419","title":"A Hybrid Swarm Intelligence Approach for Optimizing Multimodal Large Language Models Deployment in Edge-Cloud-based Federated Learning Environments","created":"2025-02-04","cited_by_count":1,"area":null},{"id":"2503.07603","title":"Should VLMs be Pre-trained with Image Data?","created":"2025-03-10","cited_by_count":1,"area":null},{"id":"2406.05149","title":"Effective Data Selection for Seismic Interpretation through Disagreement","created":"2024-06-01","cited_by_count":0,"area":null},{"id":"2501.00619","title":"A Study on Context Length and Efficient Transformers for Biomedical Image Analysis","created":"2024-12-31","cited_by_count":0,"area":null},{"id":"2510.09822","title":"Task-Aware Resolution Optimization for Visual Large Language Models","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2603.23521","title":"Chitrakshara: A Large Multilingual Multimodal Dataset for Indian languages","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2603.29211","title":"Xuanwu: Evolving General Multimodal Models into an Industrial-Grade Foundation for Content Ecosystems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2605.02200","title":"ARGUS: Policy-Adaptive Ad Governance via Evolving Reinforcement with Adversarial Umpiring","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2607.16165","title":"An Exam for Active Observers","created":"2026-07-17","cited_by_count":0,"area":null}],"next_cursor":null}