{"list":"other","total":58,"rows":[{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"1708.06733","title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain","created":"2017-08-22","cited_by_count":1106},{"id":"1712.05526","title":"Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning","created":"2017-12-15","cited_by_count":1055},{"id":"1904.03323","title":"Publicly Available Clinical BERT Embeddings","created":"2019-04-06","cited_by_count":1002},{"id":"1904.05342","title":"ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission","created":"2019-04-10","cited_by_count":493},{"id":"2011.10369","title":"ONION: A Simple and Effective Defense Against Textual Backdoor Attacks","created":"2020-11-20","cited_by_count":263},{"id":"2106.09667","title":"Poisoning and Backdooring Contrastive Learning","created":"2021-06-17","cited_by_count":151},{"id":"2204.05255","title":"Narcissus: A Practical Clean-Label Backdoor Attack with Limited Information","created":"2022-04-11","cited_by_count":103},{"id":"2111.07970","title":"Triggerless Backdoor Attack for NLP Tasks with Clean Labels","created":"2021-11-15","cited_by_count":66},{"id":"2209.11715","title":"The \"Beatrix'' Resurrections: Robust Backdoor Detection via Gram Matrices","created":"2022-09-23","cited_by_count":63},{"id":"2103.04264","title":"T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text Classification","created":"2021-03-07","cited_by_count":60},{"id":"2101.06969","title":"Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-Level Backdoor Attacks","created":"2021-01-18","cited_by_count":49},{"id":"2111.08429","title":"An Overview of Backdoor Attacks Against Deep Neural Networks and Possible Defences","created":"2021-11-16","cited_by_count":42},{"id":"1909.09702","title":"Using Clinical Notes with Time Series Data for ICU Management","created":"2019-09-12","cited_by_count":38},{"id":"2302.00219","title":"Knowledge Distillation on Graphs: A Survey","created":"2023-02-01","cited_by_count":38},{"id":"2404.12916","title":"Physical Backdoor Attack can Jeopardize Driving with Vision-Large-Language Models","created":"2024-04-19","cited_by_count":33},{"id":"2407.00203","title":"PathGen-1.6M: 1.6 Million Pathology Image-text Pairs Generation through Multi-agent Collaboration","created":"2024-06-28","cited_by_count":28},{"id":"2506.05606","title":"OPeRA: A Dataset of Observation, Persona, Rationale, and Action for Evaluating LLMs on Human Online Shopping Behavior Simulation","created":"2025-06-05","cited_by_count":28},{"id":"2003.10555","title":"ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators","created":"2020-03-23","cited_by_count":27},{"id":"2110.15763","title":"How to Leverage Multimodal EHR Data for Better Medical Predictions?","created":"2021-10-29","cited_by_count":26},{"id":"2310.07999","title":"LEMON: Lossless model expansion","created":"2023-10-12","cited_by_count":23},{"id":"2403.17155","title":"Task-Agnostic Detector for Insertion-Based Backdoor Attacks","created":"2024-03-25","cited_by_count":23},{"id":"2406.05392","title":"Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey","created":"2024-06-08","cited_by_count":23},{"id":"2402.02018","title":"The Landscape and Challenges of HPC Research and LLMs","created":"2024-02-03","cited_by_count":22},{"id":"2502.13012","title":"Towards a Design Guideline for RPA Evaluation: A Survey of Large Language Model-Based Role-Playing Agents","created":"2025-02-18","cited_by_count":22},{"id":"2101.03940","title":"Predicting Patient Outcomes with Graph Representation Learning","created":"2021-01-11","cited_by_count":21},{"id":"2409.13853","title":"Unlocking Memorization in Large Language Models with Dynamic Soft Prompting","created":"2024-09-20","cited_by_count":21},{"id":"2404.00489","title":"Prompt-SAW: Leveraging Relation-Aware Graphs for Textual Prompt Compression","created":"2024-03-30","cited_by_count":18},{"id":"2202.07183","title":"A Survey of Neural Trojan Attacks and Defenses in Deep Learning","created":"2022-02-15","cited_by_count":17},{"id":"2408.07440","title":"BAPLe: Backdoor Attacks on Medical Foundational Models using Prompt Learning","created":"2024-08-14","cited_by_count":16},{"id":"2106.01335","title":"On the Distribution, Sparsity, and Inference-time Quantization of Attention Values in Transformers","created":"2021-06-02","cited_by_count":14},{"id":"2409.07388","title":"Recent Advances in Multimodal Affective Computing: An NLP Perspective","created":"2024-09-11","cited_by_count":13},{"id":"2402.11744","title":"Machine-Generated Text Localization","created":"2024-02-19","cited_by_count":11},{"id":"1911.02782","title":"S2ORC: The Semantic Scholar Open Research Corpus","created":"2019-11-07","cited_by_count":10},{"id":"2404.17123","title":"Text Sentiment Analysis and Classification Based on Bidirectional Gated Recurrent Units (GRUs) Model","created":"2024-04-26","cited_by_count":10},{"id":"2310.02107","title":"Instances Need More Care: Rewriting Prompts for Instances with LLMs in the Loop Yields Better Zero-Shot Performance","created":"2023-10-03","cited_by_count":9},{"id":"2408.09476","title":"Advances in Multiple Instance Learning for Whole Slide Image Analysis: Techniques, Challenges, and Future Directions","created":"2024-08-18","cited_by_count":7},{"id":"2208.04946","title":"Attention Hijacking in Trojan Transformers","created":"2022-08-09","cited_by_count":6},{"id":"2507.14497","title":"Efficient Whole Slide Pathology VQA via Token Compression","created":"2025-07-19","cited_by_count":6},{"id":"2309.02521","title":"Comparative Analysis of CPU and GPU Profiling for Deep Learning Models","created":"2023-09-05","cited_by_count":4},{"id":"2412.19770","title":"Fortran2CPP: Automating Fortran-to-C++ Translation using LLMs via Multi-Turn Dialogue and Dual-Agent Integration","created":"2024-12-27","cited_by_count":4},{"id":"2312.13119","title":"Graphene: Infrastructure Security Posture Analysis with AI-generated Attack Graphs","created":"2023-12-20","cited_by_count":3},{"id":"2410.01408","title":"SHAP-CAT: A interpretable multi-modal framework enhancing WSI classification via virtual staining and shapley-value-based multimodal fusion","created":"2024-10-02","cited_by_count":3},{"id":"2411.05172","title":"ImpScore: A Learnable Metric For Quantifying The Implicitness Level of Sentence","created":"2024-11-07","cited_by_count":3},{"id":"2405.08197","title":"IHC Matters: Incorporating IHC analysis to H&E Whole Slide Image Analysis for Improved Cancer Grading via Two-stage Multimodal Bilinear Pooling Fusion","created":"2024-05-13","cited_by_count":2},{"id":"2409.07415","title":"SoK: Security and Privacy Risks of Healthcare AI","created":"2024-09-11","cited_by_count":2},{"id":"2410.12955","title":"Long-Tailed Backdoor Attack Using Dynamic Data Augmentation Operations","created":"2024-10-16","cited_by_count":2},{"id":"2303.15564","title":"Mask and Restore: Blind Backdoor Defense at Test Time with Masked Autoencoder","created":"2023-03-27","cited_by_count":1},{"id":"2503.09095","title":"Backdooring CLIP through Concept Confusion","created":"2025-03-12","cited_by_count":1},{"id":"2505.11829","title":"Class Distillation with Mahalanobis Contrast: An Efficient Training Paradigm for Pragmatic Language Understanding Tasks","created":"2025-05-17","cited_by_count":1}],"next_cursor":null}