{"list":"other","total":53,"rows":[{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"1511.04599","title":"DeepFool: a simple and accurate method to fool deep neural networks","created":"2015-11-14","cited_by_count":1318},{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771},{"id":"2312.07533","title":"VILA: On Pre-training for Visual Language Models","created":"2023-12-12","cited_by_count":692},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"2104.01778","title":"AST: Audio Spectrogram Transformer","created":"2021-04-05","cited_by_count":643},{"id":"2204.02610","title":"Efficient Test-Time Model Adaptation without Forgetting","created":"2022-04-06","cited_by_count":469},{"id":"2302.12400","title":"Towards Stable Test-Time Adaptation in Dynamic Wild World","created":"2023-02-24","cited_by_count":415},{"id":"2311.08046","title":"Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding","created":"2023-11-14","cited_by_count":371},{"id":"2303.15361","title":"A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts","created":"2023-03-27","cited_by_count":359},{"id":"2311.12320","title":"A Survey on Multimodal Large Language Models for Autonomous Driving","created":"2023-11-21","cited_by_count":290},{"id":"1810.00069","title":"Adversarial Attacks and Defences: A Survey","created":"2018-09-28","cited_by_count":259},{"id":"2402.12226","title":"AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling","created":"2024-02-19","cited_by_count":217},{"id":"2501.01957","title":"VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction","created":"2025-01-03","cited_by_count":197},{"id":"2204.05454","title":"Are Multimodal Transformers Robust to Missing Modality?","created":"2022-04-12","cited_by_count":186},{"id":"2408.05211","title":"VITA: Towards Open-Source Interactive Omni Multimodal LLM","created":"2024-08-09","cited_by_count":173},{"id":"2306.09093","title":"Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration","created":"2023-06-15","cited_by_count":172},{"id":"2304.03047","title":"ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments","created":"2023-04-06","cited_by_count":169},{"id":"2308.09936","title":"BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions","created":"2023-08-19","cited_by_count":125},{"id":"2211.07089","title":"PMR: Prototypical Modal Rebalance for Multimodal Learning","created":"2022-11-14","cited_by_count":116},{"id":"2101.03149","title":"VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency","created":"2021-01-08","cited_by_count":114},{"id":"2403.07366","title":"Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors","created":"2024-03-12","cited_by_count":106},{"id":"2108.02388","title":"TransRefer3D: Entity-and-Relation Aware Transformer for Fine-Grained 3D Visual Grounding","created":"2021-08-05","cited_by_count":86},{"id":"2204.12667","title":"MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation","created":"2022-04-27","cited_by_count":76},{"id":"2411.17558","title":"Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey","created":"2024-11-26","cited_by_count":76},{"id":"2203.01205","title":"Audio Self-supervised Learning: A Survey","created":"2022-03-02","cited_by_count":65},{"id":"2311.06612","title":"PerceptionGPT: Effectively Fusing Visual Perception into LLM","created":"2023-11-11","cited_by_count":59},{"id":"2207.11201","title":"Target-Driven Structured Transformer Planner for Vision-Language Navigation","created":"2022-07-19","cited_by_count":58},{"id":"2308.16890","title":"TouchStone: Evaluating Vision-Language Models by Language Models","created":"2023-08-31","cited_by_count":55},{"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":"2308.06879","title":"Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy Minimization","created":"2023-08-14","cited_by_count":39},{"id":"2209.11459","title":"TeST: Test-time Self-Training under Distribution Shift","created":"2022-09-23","cited_by_count":29},{"id":"2405.12139","title":"DTLLM-VLT: Diverse Text Generation for Visual Language Tracking Based on LLM","created":"2024-05-20","cited_by_count":24},{"id":"2010.14974","title":"Object Hider: Adversarial Patch Attack Against Object Detectors","created":"2020-10-28","cited_by_count":23},{"id":"2402.02968","title":"Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm Perspectives","created":"2024-02-05","cited_by_count":23},{"id":"2412.03665","title":"Personalizing Multimodal Large Language Models for Image Captioning: An Experimental Analysis","created":"2024-12-04","cited_by_count":23},{"id":"2405.14974","title":"LOVA3: Learning to Visual Question Answering, Asking and Assessment","created":"2024-05-23","cited_by_count":21},{"id":"2403.18821","title":"Real Acoustic Fields: An Audio-Visual Room Acoustics Dataset and Benchmark","created":"2024-03-27","cited_by_count":20},{"id":"2309.10787","title":"AV-SUPERB: A Multi-Task Evaluation Benchmark for Audio-Visual Representation Models","created":"2023-09-19","cited_by_count":19},{"id":"2407.00468","title":"MMEvalPro: Calibrating Multimodal Benchmarks Towards Trustworthy and Efficient Evaluation","created":"2024-06-29","cited_by_count":18},{"id":"2501.13924","title":"Towards Robust Multimodal Open-set Test-time Adaptation via Adaptive Entropy-aware Optimization","created":"2025-01-23","cited_by_count":12},{"id":"2412.19406","title":"MLLM-SUL: Multimodal Large Language Model for Semantic Scene Understanding and Localization in Traffic Scenarios","created":"2024-12-27","cited_by_count":8},{"id":"2401.00403","title":"Overcome Modal Bias in Multi-modal Federated Learning via Balanced Modality Selection","created":"2023-12-31","cited_by_count":6},{"id":"2109.14797","title":"Emergency Vehicles Audio Detection and Localization in Autonomous Driving","created":"2021-09-30","cited_by_count":5},{"id":"2408.06360","title":"Modality-Balanced Learning for Multimedia Recommendation","created":"2024-07-26","cited_by_count":5},{"id":"2503.02221","title":"Attention Bootstrapping for Multi-Modal Test-Time Adaptation","created":"2025-03-04","cited_by_count":5},{"id":"2406.19528","title":"Harnessing LLMs for Automated Video Content Analysis: An Exploratory Workflow of Short Videos on Depression","created":"2024-06-27","cited_by_count":4}],"next_cursor":null}