{"total":85,"rows":[{"id":"2204.08583","title":"VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance","created":"2022-04-18","cited_by_count":285,"area":null},{"id":"2403.08319","title":"Knowledge Conflicts for LLMs: A Survey","created":"2024-03-13","cited_by_count":283,"area":null},{"id":"2103.00123","title":"GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training","created":"2021-02-27","cited_by_count":274,"area":null},{"id":"2202.05924","title":"Compute Trends Across Three Eras of Machine Learning","created":"2022-02-11","cited_by_count":163,"area":null},{"id":"2110.12894","title":"The Efficiency Misnomer","created":"2021-10-25","cited_by_count":98,"area":null},{"id":"2208.07422","title":"Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives","created":"2022-08-15","cited_by_count":98,"area":null},{"id":"2306.05949","title":"Evaluating the Social Impact of Generative AI Systems in Systems and Society","created":"2023-06-09","cited_by_count":92,"area":null},{"id":"2403.18421","title":"BioMedLM: A 2.7B Parameter Language Model Trained On Biomedical Text","created":"2024-03-27","cited_by_count":86,"area":null},{"id":"2104.08803","title":"Consistent Accelerated Inference via Confident Adaptive Transformers","created":"2021-04-18","cited_by_count":74,"area":null},{"id":"2402.05015","title":"A Sober Look at LLMs for Material Discovery: Are They Actually Good for Bayesian Optimization Over Molecules?","created":"2024-02-07","cited_by_count":48,"area":null},{"id":"2410.11820","title":"Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws","created":"2024-10-15","cited_by_count":47,"area":null},{"id":"2207.02852","title":"Machine Learning Model Sizes and the Parameter Gap","created":"2022-07-05","cited_by_count":39,"area":null},{"id":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2209.09024","title":"Dataset Inference for Self-Supervised Models","created":"2022-09-16","cited_by_count":36,"area":null},{"id":"2305.16284","title":"DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method","created":"2023-05-25","cited_by_count":35,"area":null},{"id":"2306.07377","title":"Lost in Translation: Large Language Models in Non-English Content Analysis","created":"2023-06-12","cited_by_count":35,"area":null},{"id":"2204.10019","title":"Standing on the Shoulders of Giant Frozen Language Models","created":"2022-04-21","cited_by_count":33,"area":null},{"id":"2111.11146","title":"On the Existence of Universal Lottery Tickets","created":"2021-11-22","cited_by_count":30,"area":null},{"id":"2210.00965","title":"Green Learning: Introduction, Examples and Outlook","created":"2022-10-03","cited_by_count":30,"area":null},{"id":"2303.12961","title":"The Shaky Foundations of Clinical Foundation Models: A Survey of Large Language Models and Foundation Models for EMRs","created":"2023-03-22","cited_by_count":29,"area":null},{"id":"2106.06297","title":"Dynamic Language Models for Continuously Evolving Content","created":"2021-06-11","cited_by_count":27,"area":null},{"id":"2305.07583","title":"MoMo: Momentum Models for Adaptive Learning Rates","created":"2023-05-12","cited_by_count":24,"area":null},{"id":"2205.07890","title":"On the Difficulty of Defending Self-Supervised Learning against Model Extraction","created":"2022-05-16","cited_by_count":22,"area":null},{"id":"2303.05759","title":"An Overview on Language Models: Recent Developments and Outlook","created":"2023-03-10","cited_by_count":22,"area":null},{"id":"2306.02003","title":"On Optimal Caching and Model Multiplexing for Large Model Inference","created":"2023-06-03","cited_by_count":20,"area":null},{"id":"2401.02452","title":"The Compute Divide in Machine Learning: A Threat to Academic Contribution and Scrutiny?","created":"2024-01-04","cited_by_count":20,"area":null},{"id":"2203.12758","title":"Mokey: Enabling Narrow Fixed-Point Inference for Out-of-the-Box Floating-Point Transformer Models","created":"2022-03-23","cited_by_count":19,"area":null},{"id":"2103.04037","title":"Perspectives and Prospects on Transformer Architecture for Cross-Modal Tasks with Language and Vision","created":"2021-03-06","cited_by_count":14,"area":null},{"id":"2110.06874","title":"Automated Essay Scoring Using Transformer Models","created":"2021-10-13","cited_by_count":14,"area":null},{"id":"2303.05151","title":"Provable Data Subset Selection For Efficient Neural Network Training","created":"2023-03-09","cited_by_count":14,"area":null},{"id":"2304.05187","title":"Automatic Gradient Descent: Deep Learning without Hyperparameters","created":"2023-04-11","cited_by_count":14,"area":null},{"id":"2207.06940","title":"PASHA: Efficient HPO and NAS with Progressive Resource Allocation","created":"2022-07-14","cited_by_count":13,"area":null},{"id":"2211.17135","title":"BudgetLongformer: Can we Cheaply Pretrain a SotA Legal Language Model From Scratch?","created":"2022-11-30","cited_by_count":13,"area":null},{"id":"2203.01178","title":"DCT-Former: Efficient Self-Attention with Discrete Cosine Transform","created":"2022-03-02","cited_by_count":12,"area":null},{"id":"2405.01502","title":"Analyzing the Role of Semantic Representations in the Era of Large Language Models","created":"2024-05-02","cited_by_count":12,"area":null},{"id":"2211.12328","title":"A survey on knowledge-enhanced multimodal learning","created":"2022-11-19","cited_by_count":11,"area":null},{"id":"2410.19964","title":"Understanding Adam Requires Better Rotation Dependent Assumptions","created":"2024-10-25","cited_by_count":11,"area":null},{"id":"2102.10424","title":"GIST: Distributed Training for Large-Scale Graph Convolutional Networks","created":"2021-02-20","cited_by_count":10,"area":null},{"id":"2402.01173","title":"Efficient Prompt Caching via Embedding Similarity","created":"2024-02-02","cited_by_count":9,"area":null},{"id":"2407.02772","title":"Gradient descent with generalized Newton's method","created":"2024-07-03","cited_by_count":9,"area":null},{"id":"2308.08032","title":"Using Artificial Populations to Study Psychological Phenomena in Neural Models","created":"2023-08-15","cited_by_count":8,"area":null},{"id":"2201.12423","title":"Benchmarking Resource Usage for Efficient Distributed Deep Learning","created":"2022-01-28","cited_by_count":7,"area":null},{"id":"2205.11833","title":"Diverse Lottery Tickets Boost Ensemble from a Single Pretrained Model","created":"2022-05-24","cited_by_count":7,"area":null},{"id":"2212.11811","title":"Renormalization in the neural network-quantum field theory correspondence","created":"2022-12-22","cited_by_count":7,"area":null},{"id":"2408.01978","title":"AdvQDet: Detecting Query-Based Adversarial Attacks with Adversarial Contrastive Prompt Tuning","created":"2024-08-04","cited_by_count":7,"area":null},{"id":"2311.09480","title":"Show Your Work with Confidence: Confidence Bands for Tuning Curves","created":"2023-11-16","cited_by_count":6,"area":null},{"id":"2208.12097","title":"Training a T5 Using Lab-sized Resources","created":"2022-08-25","cited_by_count":5,"area":null},{"id":"2404.09356","title":"LLeMpower: Understanding Disparities in the Control and Access of Large Language Models","created":"2024-04-14","cited_by_count":5,"area":null},{"id":"2506.06644","title":"Spark Transformer: Reactivating Sparsity in FFN and Attention","created":"2025-06-07","cited_by_count":5,"area":null},{"id":"2509.18886","title":"Confidential LLM Inference: Performance and Cost Across CPU and GPU TEEs","created":"2025-09-23","cited_by_count":5,"area":null},{"id":"2210.10246","title":"Tempo: Accelerating Transformer-Based Model Training through Memory Footprint Reduction","created":"2022-10-19","cited_by_count":4,"area":null},{"id":"2301.07006","title":"Which Model Shall I Choose? Cost/Quality Trade-offs for Text Classification Tasks","created":"2023-01-17","cited_by_count":4,"area":null},{"id":"2302.12128","title":"On the Generalization Ability of Retrieval-Enhanced Transformers","created":"2023-02-23","cited_by_count":4,"area":null},{"id":"2305.06085","title":"FedSOV: Federated Model Secure Ownership Verification with Unforgeable Signature","created":"2023-05-10","cited_by_count":4,"area":null},{"id":"2310.01959","title":"Beyond Labeling Oracles: What does it mean to steal ML models?","created":"2023-10-03","cited_by_count":4,"area":null},{"id":"2408.06062","title":"On Tables with Numbers, with Numbers","created":"2024-08-12","cited_by_count":4,"area":null},{"id":"2410.05930","title":"Fortify Your Foundations: Practical Privacy and Security for Foundation Model Deployments In The Cloud","created":"2024-10-08","cited_by_count":4,"area":null},{"id":"2312.04740","title":"Train 'n Trade: Foundations of Parameter Markets","created":"2023-12-07","cited_by_count":3,"area":null},{"id":"2406.12670","title":"Stealth edits to large language models","created":"2024-06-18","cited_by_count":3,"area":null},{"id":"2501.10258","title":"DADA: Dual Averaging with Distance Adaptation","created":"2025-01-17","cited_by_count":3,"area":null},{"id":"2508.15478","title":"SLM-Bench: A Comprehensive Benchmark of Small Language Models on Environmental Impacts--Extended Version","created":"2025-08-21","cited_by_count":3,"area":null},{"id":"2207.10702","title":"Efficient model compression with Random Operation Access Specific Tile (ROAST) hashing","created":"2022-07-21","cited_by_count":2,"area":null},{"id":"2303.02411","title":"The Contribution of Knowledge in Visiolinguistic Learning: A Survey on Tasks and Challenges","created":"2023-03-04","cited_by_count":2,"area":null},{"id":"2305.06677","title":"INGENIOUS: Using Informative Data Subsets for Efficient Pre-Training of Language Models","created":"2023-05-11","cited_by_count":2,"area":null},{"id":"2305.15070","title":"Annotation Imputation to Individualize Predictions: Initial Studies on Distribution Dynamics and Model Predictions","created":"2023-05-24","cited_by_count":2,"area":null},{"id":"2312.03912","title":"Collaboration or Corporate Capture? Quantifying NLP's Reliance on Industry Artifacts and Contributions","created":"2023-12-06","cited_by_count":2,"area":null},{"id":"2410.05331","title":"Taylor Unswift: Secured Weight Release for Large Language Models via Taylor Expansion","created":"2024-10-06","cited_by_count":2,"area":null},{"id":"2210.16892","title":"Partitioned Gradient Matching-based Data Subset Selection for Compute-Efficient Robust ASR Training","created":"2022-10-30","cited_by_count":1,"area":null},{"id":"2212.03749","title":"Memorization of Named Entities in Fine-tuned BERT Models","created":"2022-12-07","cited_by_count":1,"area":null},{"id":"2304.04222","title":"CILIATE: Towards Fairer Class-based Incremental Learning by Dataset and Training Refinement","created":"2023-04-09","cited_by_count":1,"area":null},{"id":"2308.08234","title":"Challenges and Opportunities of Using Transformer-Based Multi-Task Learning in NLP Through ML Lifecycle: A Survey","created":"2023-08-16","cited_by_count":1,"area":null},{"id":"2310.10102","title":"KAKURENBO: Adaptively Hiding Samples in Deep Neural Network Training","created":"2023-10-16","cited_by_count":1,"area":null},{"id":"2311.04016","title":"Exploring Dataset-Scale Indicators of Data Quality","created":"2023-11-07","cited_by_count":1,"area":null},{"id":"2311.18598","title":"Generalisable Agents for Neural Network Optimisation","created":"2023-11-30","cited_by_count":1,"area":null},{"id":"2402.12216","title":"Copyleft for Alleviating AIGC Copyright Dilemma: What-if Analysis, Public Perception and Implications","created":"2024-02-19","cited_by_count":1,"area":null},{"id":"2407.08890","title":"DeepCodeProbe: Towards Understanding What Models Trained on Code Learn","created":"2024-07-11","cited_by_count":1,"area":null},{"id":"2505.07345","title":"QUPID: Quantified Understanding for Enhanced Performance, Insights, and Decisions in Korean Search Engines","created":"2025-05-12","cited_by_count":1,"area":null},{"id":"2203.06668","title":"Towards Personalized Intelligence at Scale","created":"2022-03-13","cited_by_count":0,"area":null},{"id":"2306.13236","title":"Document Image Cleaning using Budget-Aware Black-Box Approximation","created":"2023-06-22","cited_by_count":0,"area":null},{"id":"2310.18324","title":"\"A Nova Eletricidade: Aplica\\c{c}\\~oes, Riscos e Tend\\^encias da IA Moderna -- \"The New Electricity\": Applications, Risks, and Trends in Current AI","created":"2023-10-08","cited_by_count":0,"area":null},{"id":"2312.00855","title":"Refine, Discriminate and Align: Stealing Encoders via Sample-Wise Prototypes and Multi-Relational Extraction","created":"2023-12-01","cited_by_count":0,"area":null},{"id":"2403.15455","title":"Improving Sampling Methods for Fine-tuning SentenceBERT in Text Streams","created":"2024-03-18","cited_by_count":0,"area":null},{"id":"2503.22810","title":"Harnessing uncertainty when learning through Equilibrium Propagation in neural networks","created":"2025-03-28","cited_by_count":0,"area":null},{"id":"2507.07414","title":"GNN-CNN: An Efficient Hybrid Model of Convolutional and Graph Neural Networks for Text Representation","created":"2025-07-10","cited_by_count":0,"area":null},{"id":"2607.12612","title":"Translation as a Computationally Efficient Bridge: Feasibility of English BERT for Low-Resource Languages","created":"2026-07-14","cited_by_count":0,"area":null}],"next_cursor":null}