{"list":"other","total":72,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1606.04797","title":"V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation","created":"2016-06-15","cited_by_count":2292},{"id":"1908.09635","title":"A Survey on Bias and Fairness in Machine Learning","created":"2019-08-23","cited_by_count":1917},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"1705.09406","title":"Multimodal Machine Learning: A Survey and Taxonomy","created":"2017-05-26","cited_by_count":1013},{"id":"2309.14525","title":"Aligning Large Multimodal Models with Factually Augmented RLHF","created":"2023-09-25","cited_by_count":712},{"id":"1801.04264","title":"Real-world Anomaly Detection in Surveillance Videos","created":"2018-01-12","cited_by_count":577},{"id":"1712.09867","title":"Future Frame Prediction for Anomaly Detection -- A New Baseline","created":"2017-12-28","cited_by_count":391},{"id":"2306.13213","title":"Visual Adversarial Examples Jailbreak Aligned Large Language Models","created":"2023-06-22","cited_by_count":328},{"id":"2006.06195","title":"Large-Scale Adversarial Training for Vision-and-Language Representation Learning","created":"2020-06-11","cited_by_count":327},{"id":"2303.14814","title":"WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation","created":"2023-03-26","cited_by_count":315},{"id":"2209.02299","title":"A Survey of Machine Unlearning","created":"2022-09-06","cited_by_count":312},{"id":"2303.17591","title":"Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models","created":"2023-03-30","cited_by_count":301},{"id":"2310.18961","title":"AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection","created":"2023-10-29","cited_by_count":271},{"id":"1910.07969","title":"On Completeness-aware Concept-Based Explanations in Deep Neural Networks","created":"2019-10-17","cited_by_count":239},{"id":"2007.04687","title":"Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision","created":"2020-07-09","cited_by_count":238},{"id":"2104.10036","title":"VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localization","created":"2021-04-20","cited_by_count":223},{"id":"2305.20086","title":"Understanding and Mitigating Copying in Diffusion Models","created":"2023-05-31","cited_by_count":209},{"id":"2204.05454","title":"Are Multimodal Transformers Robust to Missing Modality?","created":"2022-04-12","cited_by_count":186},{"id":"2203.14960","title":"Domino: Discovering Systematic Errors with Cross-Modal Embeddings","created":"2022-03-24","cited_by_count":156},{"id":"2308.10741","title":"On the Adversarial Robustness of Multi-Modal Foundation Models","created":"2023-08-21","cited_by_count":145},{"id":"2206.09391","title":"Towards Adversarial Attack on Vision-Language Pre-training Models","created":"2022-06-19","cited_by_count":144},{"id":"2303.00601","title":"Multimodal Industrial Anomaly Detection via Hybrid Fusion","created":"2023-03-01","cited_by_count":139},{"id":"2205.01397","title":"Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)","created":"2022-05-03","cited_by_count":138},{"id":"2312.10665","title":"Silkie: Preference Distillation for Large Visual Language Models","created":"2023-12-17","cited_by_count":130},{"id":"2012.07923","title":"Improving model calibration with accuracy versus uncertainty optimization","created":"2020-12-14","cited_by_count":123},{"id":"2308.11681","title":"VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection","created":"2023-08-22","cited_by_count":123},{"id":"2308.07026","title":"AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learning","created":"2023-08-14","cited_by_count":103},{"id":"2104.06064","title":"Mixed supervision for surface-defect detection: from weakly to fully supervised learning","created":"2021-04-13","cited_by_count":101},{"id":"2302.08888","title":"Multimodal Federated Learning via Contrastive Representation Ensemble","created":"2023-02-17","cited_by_count":86},{"id":"2306.02050","title":"Provable Dynamic Fusion for Low-Quality Multimodal Data","created":"2023-06-03","cited_by_count":82},{"id":"2401.12915","title":"Red Teaming Visual Language Models","created":"2024-01-23","cited_by_count":65},{"id":"2107.00758","title":"The Spotlight: A General Method for Discovering Systematic Errors in Deep Learning Models","created":"2021-07-01","cited_by_count":63},{"id":"2311.00453","title":"CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detection","created":"2023-11-01","cited_by_count":58},{"id":"2101.02032","title":"Socially Responsible AI Algorithms: Issues, Purposes, and Challenges","created":"2021-01-01","cited_by_count":56},{"id":"2204.04588","title":"Robust Cross-Modal Representation Learning with Progressive Self-Distillation","created":"2022-04-10","cited_by_count":55},{"id":"2306.09486","title":"FedMultimodal: A Benchmark For Multimodal Federated Learning","created":"2023-06-15","cited_by_count":51},{"id":"1803.07464","title":"VQA-E: Explaining, Elaborating, and Enhancing Your Answers for Visual Questions","created":"2018-03-20","cited_by_count":50},{"id":"2105.07878","title":"A Review on Explainability in Multimodal Deep Neural Nets","created":"2021-05-17","cited_by_count":46},{"id":"2310.02224","title":"Can Language Models be Instructed to Protect Personal Information?","created":"2023-10-03","cited_by_count":46},{"id":"2309.15379","title":"A Content-Driven Micro-Video Recommendation Dataset at Scale","created":"2023-09-27","cited_by_count":45},{"id":"2310.19070","title":"Myriad: Large Multimodal Model by Applying Vision Experts for Industrial Anomaly Detection","created":"2023-10-29","cited_by_count":39},{"id":"2310.00108","title":"Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Study","created":"2023-09-29","cited_by_count":38},{"id":"2012.08673","title":"A Closer Look at the Robustness of Vision-and-Language Pre-trained Models","created":"2020-12-15","cited_by_count":37},{"id":"1909.13550","title":"Well-calibrated Model Uncertainty with Temperature Scaling for Dropout Variational Inference","created":"2019-09-30","cited_by_count":36},{"id":"2106.06683","title":"Assessing Multilingual Fairness in Pre-trained Multimodal Representations","created":"2021-06-12","cited_by_count":35},{"id":"2311.01723","title":"Towards Calibrated Robust Fine-Tuning of Vision-Language Models","created":"2023-11-03","cited_by_count":35},{"id":"2203.02013","title":"DIME: Fine-grained Interpretations of Multimodal Models via Disentangled Local Explanations","created":"2022-03-03","cited_by_count":34},{"id":"2310.02835","title":"Delving into CLIP latent space for Video Anomaly Recognition","created":"2023-10-04","cited_by_count":27},{"id":"2306.05731","title":"Multimodal Explainable Artificial Intelligence: A Comprehensive Review of Methodological Advances and Future Research Directions","created":"2023-06-09","cited_by_count":25},{"id":"2104.02000","title":"Can audio-visual integration strengthen robustness under multimodal attacks?","created":"2021-04-05","cited_by_count":23},{"id":"2312.07424","title":"How Well Does GPT-4V(ision) Adapt to Distribution Shifts? A Preliminary Investigation","created":"2023-12-12","cited_by_count":22},{"id":"2004.07173","title":"Bias in Multimodal AI: Testbed for Fair Automatic Recruitment","created":"2020-04-15","cited_by_count":21},{"id":"2206.12714","title":"Defending Multimodal Fusion Models against Single-Source Adversaries","created":"2022-06-25","cited_by_count":20},{"id":"2212.14453","title":"Learning Multimodal Data Augmentation in Feature Space","created":"2022-12-29","cited_by_count":18},{"id":"2306.01265","title":"Calibrating Multimodal Learning","created":"2023-06-02","cited_by_count":17},{"id":"2304.03646","title":"Fairness through Aleatoric Uncertainty","created":"2023-04-07","cited_by_count":16},{"id":"2309.10283","title":"FRAMU: Attention-based Machine Unlearning using Federated Reinforcement Learning","created":"2023-09-19","cited_by_count":13},{"id":"2309.17319","title":"Building Privacy-Preserving and Secure Geospatial Artificial Intelligence Foundation Models","created":"2023-09-29","cited_by_count":12},{"id":"2012.08637","title":"Multi-Modal Anomaly Detection for Unstructured and Uncertain Environments","created":"2020-12-15","cited_by_count":11},{"id":"2205.08383","title":"Bias and Fairness on Multimodal Emotion Detection Algorithms","created":"2022-05-11","cited_by_count":10},{"id":"2310.09926","title":"Estimating Uncertainty in Multimodal Foundation Models using Public Internet Data","created":"2023-10-15","cited_by_count":10},{"id":"2310.04929","title":"DISCOVER: Making Vision Networks Interpretable via Competition and Dissection","created":"2023-10-07","cited_by_count":8},{"id":"2306.08173","title":"Safeguarding Data in Multimodal AI: A Differentially Private Approach to CLIP Training","created":"2023-06-13","cited_by_count":7},{"id":"2210.14556","title":"Multimodal Contrastive Learning via Uni-Modal Coding and Cross-Modal Prediction for Multimodal Sentiment Analysis","created":"2022-10-26","cited_by_count":6},{"id":"2310.17373","title":"Causality-Inspired Fair Representation Learning for Multimodal Recommendation","created":"2023-10-26","cited_by_count":5},{"id":"2312.07550","title":"Understanding (Un)Intended Memorization in Text-to-Image Generative Models","created":"2023-12-06","cited_by_count":5},{"id":"2310.04971","title":"Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shift","created":"2023-10-08","cited_by_count":4},{"id":"2308.13513","title":"Unveiling the Role of Message Passing in Dual-Privacy Preservation on GNNs","created":"2023-08-25","cited_by_count":3}],"next_cursor":null}