{"list":"other","total":85,"rows":[{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"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":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"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":"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":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","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":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2307.16789","title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","created":"2023-07-31","cited_by_count":1947},{"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},{"id":"2310.02255","title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","created":"2023-10-03","cited_by_count":1614},{"id":"2203.10244","title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","created":"2022-03-19","cited_by_count":1479},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"2404.07972","title":"OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments","created":"2024-04-11","cited_by_count":1195},{"id":"2408.01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","created":"2024-08-03","cited_by_count":1079},{"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":"2404.16821","title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","created":"2024-04-25","cited_by_count":1050},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"1801.09414","title":"CosFace: Large Margin Cosine Loss for Deep Face Recognition","created":"2018-01-29","cited_by_count":971},{"id":"2307.16125","title":"SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension","created":"2023-07-30","cited_by_count":940},{"id":"2405.09818","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","created":"2024-05-16","cited_by_count":927},{"id":"1704.03976","title":"Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning","created":"2017-04-13","cited_by_count":920},{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2406.16860","title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","created":"2024-06-24","cited_by_count":838},{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708},{"id":"2407.07726","title":"PaliGemma: A versatile 3B VLM for transfer","created":"2024-07-10","cited_by_count":696},{"id":"2312.07533","title":"VILA: On Pre-training for Visual Language Models","created":"2023-12-12","cited_by_count":692},{"id":"1905.13319","title":"MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms","created":"2019-05-30","cited_by_count":662},{"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":"2407.11691","title":"VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models","created":"2024-07-16","cited_by_count":455},{"id":"2306.05301","title":"ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases","created":"2023-06-08","cited_by_count":393},{"id":"2311.06607","title":"Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models","created":"2023-11-11","cited_by_count":357},{"id":"2406.08464","title":"Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing","created":"2024-06-12","cited_by_count":346},{"id":"2103.02406","title":"Multi-attentional Deepfake Detection","created":"2021-03-03","cited_by_count":341},{"id":"2405.02246","title":"What matters when building vision-language models?","created":"2024-05-03","cited_by_count":326},{"id":"1710.07300","title":"FigureQA: An Annotated Figure Dataset for Visual Reasoning","created":"2017-10-19","cited_by_count":319},{"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":"2410.19168","title":"MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark","created":"2024-10-24","cited_by_count":288},{"id":"2410.23262","title":"EMMA: End-to-End Multimodal Model for Autonomous Driving","created":"2024-10-30","cited_by_count":231},{"id":"2408.16500","title":"CogVLM2: Visual Language Models for Image and Video Understanding","created":"2024-08-29","cited_by_count":217},{"id":"2405.01483","title":"MANTIS: Interleaved Multi-Image Instruction Tuning","created":"2024-05-02","cited_by_count":216},{"id":"2312.11370","title":"G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model","created":"2023-12-18","cited_by_count":210},{"id":"2112.03109","title":"General Facial Representation Learning in a Visual-Linguistic Manner","created":"2021-12-06","cited_by_count":195},{"id":"2105.05486","title":"TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text","created":"2021-05-12","cited_by_count":171},{"id":"1710.00925","title":"Fine-Grained Head Pose Estimation Without Keypoints","created":"2017-10-02","cited_by_count":163},{"id":"2408.15998","title":"Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders","created":"2024-08-28","cited_by_count":139},{"id":"1901.07884","title":"Rank consistent ordinal regression for neural networks with application to age estimation","created":"2019-01-20","cited_by_count":133},{"id":"2407.08739","title":"MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine","created":"2024-07-11","cited_by_count":113},{"id":"2410.02761","title":"FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models","created":"2024-10-03","cited_by_count":113},{"id":"2109.04425","title":"Talk-to-Edit: Fine-Grained Facial Editing via Dialog","created":"2021-09-09","cited_by_count":102},{"id":"2402.11690","title":"Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning","created":"2024-02-18","cited_by_count":73},{"id":"2202.12555","title":"6D Rotation Representation For Unconstrained Head Pose Estimation","created":"2022-02-25","cited_by_count":64},{"id":"1807.09959","title":"Iterative Crowd Counting","created":"2018-07-26","cited_by_count":48},{"id":"2402.04178","title":"SHIELD : An Evaluation Benchmark for Face Spoofing and Forgery Detection with Multimodal Large Language Models","created":"2024-02-06","cited_by_count":40},{"id":"2401.13641","title":"How Good is ChatGPT at Face Biometrics? A First Look into Recognition, Soft Biometrics, and Explainability","created":"2024-01-24","cited_by_count":34},{"id":"2403.12960","title":"FaceXFormer: A Unified Transformer for Facial Analysis","created":"2024-03-19","cited_by_count":34},{"id":"2410.10139","title":"MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models","created":"2024-10-14","cited_by_count":33},{"id":"2408.11424","title":"EMO-LLaMA: Enhancing Facial Emotion Understanding with Instruction Tuning","created":"2024-08-21","cited_by_count":28},{"id":"2203.14448","title":"Decoupled Multi-task Learning with Cyclical Self-Regulation for Face Parsing","created":"2022-03-28","cited_by_count":26},{"id":"2410.08474","title":"SPORTU: A Comprehensive Sports Understanding Benchmark for Multimodal Large Language Models","created":"2024-10-11","cited_by_count":24},{"id":"2410.23831","title":"FRoundation: Are Foundation Models Ready for Face Recognition?","created":"2024-10-31","cited_by_count":23},{"id":"2401.15174","title":"LaMI: Large Language Models for Multi-Modal Human-Robot Interaction","created":"2024-01-26","cited_by_count":21},{"id":"2405.05956","title":"Probing Multimodal LLMs as World Models for Driving","created":"2024-05-09","cited_by_count":20},{"id":"2407.18961","title":"MMAU: A Holistic Benchmark of Agent Capabilities Across Diverse Domains","created":"2024-07-18","cited_by_count":19},{"id":"2405.19100","title":"Enhancing Zero-Shot Facial Expression Recognition by LLM Knowledge Transfer","created":"2024-05-29","cited_by_count":18},{"id":"2412.08647","title":"SegFace: Face Segmentation of Long-Tail Classes","created":"2024-12-11","cited_by_count":18},{"id":"2101.07034","title":"AGRNet: Adaptive Graph Representation Learning and Reasoning for Face Parsing","created":"2021-01-18","cited_by_count":16},{"id":"2407.08515","title":"15M Multimodal Facial Image-Text Dataset","created":"2024-07-11","cited_by_count":14},{"id":"2403.09500","title":"Faceptor: A Generalist Model for Face Perception","created":"2024-03-14","cited_by_count":13},{"id":"2405.11537","title":"VR-GPT: Visual Language Model for Intelligent Virtual Reality Applications","created":"2024-05-19","cited_by_count":9},{"id":"2209.09111","title":"DeePhy: On Deepfake Phylogeny","created":"2022-09-19","cited_by_count":8},{"id":"2303.15122","title":"Parameter Efficient Local Implicit Image Function Network for Face Segmentation","created":"2023-03-27","cited_by_count":8},{"id":"2403.06606","title":"Distributionally Generative Augmentation for Fair Facial Attribute Classification","created":"2024-03-11","cited_by_count":8},{"id":"2405.09059","title":"Task-adaptive Q-Face","created":"2024-05-15","cited_by_count":5},{"id":"2404.14406","title":"Hyp-OC: Hyperbolic One Class Classification for Face Anti-Spoofing","created":"2024-04-22","cited_by_count":3},{"id":"2312.07886","title":"Modality Plug-and-Play: Elastic Modality Adaptation in Multimodal LLMs for Embodied AI","created":"2023-12-13","cited_by_count":2},{"id":"2105.06746","title":"Facial Age Estimation using Convolutional Neural Networks","created":"2021-05-14","cited_by_count":1}],"next_cursor":null}