{"total":59,"rows":[{"id":"2106.04426","title":"Hash Layers For Large Sparse Models","created":"2021-06-08","cited_by_count":237,"area":null},{"id":"2111.09509","title":"How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVEN","created":"2021-11-18","cited_by_count":124,"area":null},{"id":"2301.10472","title":"XLM-V: Overcoming the Vocabulary Bottleneck in Multilingual Masked Language Models","created":"2023-01-25","cited_by_count":88,"area":null},{"id":"2102.11972","title":"Do Transformer Modifications Transfer Across Implementations and Applications?","created":"2021-02-23","cited_by_count":87,"area":null},{"id":"2102.02557","title":"Adaptive Semiparametric Language Models","created":"2021-02-04","cited_by_count":83,"area":null},{"id":"2110.00685","title":"Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classification","created":"2021-10-01","cited_by_count":67,"area":null},{"id":"2201.12431","title":"Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval","created":"2022-01-28","cited_by_count":60,"area":null},{"id":"2212.01349","title":"Nonparametric Masked Language Modeling","created":"2022-12-02","cited_by_count":40,"area":null},{"id":"2411.09009","title":"Cut Your Losses in Large-Vocabulary Language Models","created":"2024-11-13","cited_by_count":40,"area":null},{"id":"2102.12459","title":"When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute","created":"2021-02-24","cited_by_count":34,"area":null},{"id":"2105.06548","title":"Not All Memories are Created Equal: Learning to Forget by Expiring","created":"2021-05-13","cited_by_count":32,"area":null},{"id":"2110.02121","title":"Optimization with Constraint Learning: A Framework and Survey","created":"2021-10-05","cited_by_count":28,"area":null},{"id":"2201.09680","title":"Relational Memory Augmented Language Models","created":"2022-01-24","cited_by_count":24,"area":null},{"id":"2212.02475","title":"Meta-Learning Fast Weight Language Models","created":"2022-12-05","cited_by_count":21,"area":null},{"id":"2502.01637","title":"Scaling Embedding Layers in Language Models","created":"2025-02-03","cited_by_count":20,"area":null},{"id":"2301.12860","title":"Massively Scaling Heteroscedastic Classifiers","created":"2023-01-30","cited_by_count":11,"area":null},{"id":"2406.16508","title":"Large Vocabulary Size Improves Large Language Models","created":"2024-06-24","cited_by_count":11,"area":null},{"id":"2104.03474","title":"Revisiting Simple Neural Probabilistic Language Models","created":"2021-04-08","cited_by_count":10,"area":null},{"id":"2104.08225","title":"Distantly Supervised Relation Extraction with Sentence Reconstruction and Knowledge Base Priors","created":"2021-04-16","cited_by_count":8,"area":null},{"id":"2404.00397","title":"An Analysis of BPE Vocabulary Trimming in Neural Machine Translation","created":"2024-03-30","cited_by_count":7,"area":null},{"id":"2203.10692","title":"Better Language Model with Hypernym Class Prediction","created":"2022-03-21","cited_by_count":5,"area":null},{"id":"2508.01010","title":"v-PuNNs: van der Put Neural Networks for Transparent Ultrametric Representation Learning","created":"2025-08-01","cited_by_count":5,"area":null},{"id":"2601.12145","title":"Threshold Differential Attention for Sink-Free, Ultra-Sparse, and Non-Dispersive Language Modeling","created":"2026-01-17","cited_by_count":5,"area":null},{"id":"2108.07129","title":"Autoencoders as Tools for Program Synthesis","created":"2021-08-16","cited_by_count":4,"area":null},{"id":"2205.02724","title":"Implicit N-grams Induced by Recurrence","created":"2022-05-05","cited_by_count":4,"area":null},{"id":"2207.07475","title":"Stable Invariant Models via Koopman Spectra","created":"2022-07-15","cited_by_count":4,"area":null},{"id":"2306.01705","title":"The Information Pathways Hypothesis: Transformers are Dynamic Self-Ensembles","created":"2023-06-02","cited_by_count":4,"area":null},{"id":"2410.22669","title":"A Walsh Hadamard Derived Linear Vector Symbolic Architecture","created":"2024-10-30","cited_by_count":4,"area":null},{"id":"2105.02103","title":"Prototype Memory for Large-scale Face Representation Learning","created":"2021-05-05","cited_by_count":3,"area":null},{"id":"2109.04030","title":"Bag of Tricks for Optimizing Transformer Efficiency","created":"2021-09-09","cited_by_count":3,"area":null},{"id":"2207.03575","title":"Online Trajectory Prediction for Metropolitan Scale Mobility Digital Twin","created":"2022-06-21","cited_by_count":3,"area":null},{"id":"2310.19731","title":"ViR: Towards Efficient Vision Retention Backbones","created":"2023-10-30","cited_by_count":2,"area":null},{"id":"2402.03142","title":"Less is KEN: a Universal and Simple Non-Parametric Pruning Algorithm for Large Language Models","created":"2024-02-05","cited_by_count":2,"area":null},{"id":"2404.12460","title":"NLP-enabled Trajectory Map-matching in Urban Road Networks using a Transformer-based Encoder-decoder","created":"2024-04-18","cited_by_count":2,"area":null},{"id":"2405.06038","title":"From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks","created":"2024-05-09","cited_by_count":2,"area":null},{"id":"2406.06739","title":"Scaling the Vocabulary of Non-autoregressive Models for Efficient Generative Retrieval","created":"2024-06-10","cited_by_count":2,"area":null},{"id":"2503.15002","title":"Scalable Trajectory-User Linking with Dual-Stream Representation Networks","created":"2025-03-19","cited_by_count":2,"area":null},{"id":"2505.10202","title":"VQ-Logits: Compressing the Output Bottleneck of Large Language Models via Vector Quantized Logits","created":"2025-05-15","cited_by_count":2,"area":null},{"id":"2507.16323","title":"SpeLLM: Character-Level Multi-Head Decoding","created":"2025-07-22","cited_by_count":2,"area":null},{"id":"2509.11782","title":"Multimodal Regression for Enzyme Turnover Rates Prediction","created":"2025-09-15","cited_by_count":2,"area":null},{"id":"2605.29379","title":"BrahmicTokenizer-131K: An Indic-Capable Drop-In Replacement for o200k_base","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2109.08249","title":"Regularized Training of Nearest Neighbor Language Models","created":"2021-09-16","cited_by_count":1,"area":null},{"id":"2208.06874","title":"Fast Vocabulary Projection Method via Clustering for Multilingual Machine Translation on GPU","created":"2022-08-14","cited_by_count":1,"area":null},{"id":"2208.09625","title":"SPOT: Knowledge-Enhanced Language Representations for Information Extraction","created":"2022-08-20","cited_by_count":1,"area":null},{"id":"2212.07081","title":"Trajectory-User Linking Is Easier Than You Think","created":"2022-12-14","cited_by_count":1,"area":null},{"id":"2306.04235","title":"MobileNMT: Enabling Translation in 15MB and 30ms","created":"2023-06-07","cited_by_count":1,"area":null},{"id":"2411.06371","title":"LLM Vocabulary Compression for Low-Compute Environments","created":"2024-11-10","cited_by_count":1,"area":null},{"id":"2502.00617","title":"Efficient Language Modeling for Low-Resource Settings with Hybrid RNN-Transformer Architectures","created":"2025-02-02","cited_by_count":1,"area":null},{"id":"2609.31291","title":"Softmax Reparameterization for Output-Head Quantization","created":"2026-09-25","cited_by_count":1,"area":null},{"id":"2305.11462","title":"Extending Memory for Language Modelling","created":"2023-05-19","cited_by_count":0,"area":null},{"id":"2311.08123","title":"Memory-efficient Stochastic methods for Memory-based Transformers","created":"2023-11-14","cited_by_count":0,"area":null},{"id":"2403.06520","title":"How to Understand Named Entities: Using Common Sense for News Captioning","created":"2024-03-11","cited_by_count":0,"area":null},{"id":"2504.19209","title":"Dynamic Embedded Topic Models: properties and recommendations based on diverse corpora","created":"2025-04-27","cited_by_count":0,"area":null},{"id":"2505.00929","title":"Compact Recurrent Transformer with Persistent Memory","created":"2025-05-02","cited_by_count":0,"area":null},{"id":"2605.09751","title":"Language Models Without a Trainable Input Embedding Table: Learning from Fixed Minimal Binary Token Codes","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2606.19528","title":"Techniques for Peak Memory Reduction for LoRA Fine-tuning of LLMs on Edge Devices","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2608.24079","title":"Keeping the Index Open: The Recommendation-Side Cost of Shared Search and Recommendation","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.27460","title":"Accelerating LLM Inference via Vector Index Based Output Embeddings","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2609.15528","title":"To Each Language Its Tokenizer: Modular Tokenizers for Efficient Multilingual LLMs","created":"2026-09-14","cited_by_count":0,"area":null}],"next_cursor":null}