{"total":34,"rows":[{"id":"2110.01515","title":"A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning","created":"2021-10-04","cited_by_count":82,"area":null},{"id":"2305.18465","title":"Federated Learning of Gboard Language Models with Differential Privacy","created":"2023-05-29","cited_by_count":66,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2108.11333","title":"Lightweight Self-Attentive Sequential Recommendation","created":"2021-08-25","cited_by_count":22,"area":null},{"id":"2303.01980","title":"Towards energy-efficient Deep Learning: An overview of energy-efficient approaches along the Deep Learning Lifecycle","created":"2023-02-05","cited_by_count":14,"area":null},{"id":"2311.15578","title":"Experimental Analysis of Large-scale Learnable Vector Storage Compression","created":"2023-11-27","cited_by_count":12,"area":null},{"id":"2109.02471","title":"Binary Code based Hash Embedding for Web-scale Applications","created":"2021-08-24","cited_by_count":11,"area":null},{"id":"2109.06679","title":"Efficient Inference for Multilingual Neural Machine Translation","created":"2021-09-14","cited_by_count":10,"area":null},{"id":"2208.05648","title":"Embedding Compression with Hashing for Efficient Representation Learning in Large-Scale Graph","created":"2022-08-11","cited_by_count":10,"area":null},{"id":"2108.09128","title":"Semi-supervised Network Embedding with Differentiable Deep Quantisation","created":"2021-08-20","cited_by_count":7,"area":null},{"id":"2210.07904","title":"HashFormers: Towards Vocabulary-independent Pre-trained Transformers","created":"2022-10-14","cited_by_count":6,"area":null},{"id":"2403.14001","title":"Evaluating Unsupervised Dimensionality Reduction Methods for Pretrained Sentence Embeddings","created":"2024-03-20","cited_by_count":6,"area":null},{"id":"2210.15379","title":"MorphTE: Injecting Morphology in Tensorized Embeddings","created":"2022-10-27","cited_by_count":5,"area":null},{"id":"2103.14455","title":"Projected Hamming Dissimilarity for Bit-Level Importance Coding in Collaborative Filtering","created":"2021-03-26","cited_by_count":4,"area":null},{"id":"2103.15330","title":"Extending Multi-Sense Word Embedding to Phrases and Sentences for Unsupervised Semantic Applications","created":"2021-03-29","cited_by_count":3,"area":null},{"id":"2104.08677","title":"From Fully Trained to Fully Random Embeddings: Improving Neural Machine Translation with Compact Word Embedding Tables","created":"2021-04-18","cited_by_count":2,"area":null},{"id":"2106.06440","title":"Learning Compositional Shape Priors for Few-Shot 3D Reconstruction","created":"2021-06-11","cited_by_count":2,"area":null},{"id":"2410.10180","title":"Gaussian Mixture Vector Quantization with Aggregated Categorical Posterior","created":"2024-10-14","cited_by_count":2,"area":null},{"id":"2407.16174","title":"Pixel Embedding: Fully Quantized Convolutional Neural Network with Differentiable Lookup Table","created":"2024-07-23","cited_by_count":1,"area":null},{"id":"2410.21548","title":"MultiTok: Variable-Length Tokenization for Efficient LLMs Adapted from LZW Compression","created":"2024-10-28","cited_by_count":1,"area":null},{"id":"2606.28057","title":"MultiHashFormer: Hash-based Generative Language Models","created":"2026-06-26","cited_by_count":1,"area":null},{"id":"2108.09136","title":"Unsupervised Domain-adaptive Hash for Networks","created":"2021-08-20","cited_by_count":0,"area":null},{"id":"2111.10320","title":"Toward Compact Parameter Representations for Architecture-Agnostic Neural Network Compression","created":"2021-11-19","cited_by_count":0,"area":null},{"id":"2211.12715","title":"Embedding Compression for Text Classification Using Dictionary Screening","created":"2022-11-23","cited_by_count":0,"area":null},{"id":"2304.02481","title":"Rediscovering Hashed Random Projections for Efficient Quantization of Contextualized Sentence Embeddings","created":"2023-03-13","cited_by_count":0,"area":null},{"id":"2407.12342","title":"Word Embedding Dimension Reduction via Weakly-Supervised Feature Selection","created":"2024-07-17","cited_by_count":0,"area":null},{"id":"2505.02266","title":"Parameter-Efficient Transformer Embeddings","created":"2025-05-04","cited_by_count":0,"area":null},{"id":"2506.01254","title":"Memory-Efficient FastText: A Comprehensive Approach Using Double-Array Trie Structures and Mark-Compact Memory Management","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2508.00220","title":"Semantic Compression for Word and Sentence Embeddings using Discrete Wavelet Transform","created":"2025-07-31","cited_by_count":0,"area":null},{"id":"2510.06125","title":"Downsized and Compromised?: Assessing the Faithfulness of Model Compression","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2604.24940","title":"ADE: Adaptive Dictionary Embeddings -- Scaling Multi-Anchor Representations to Large Language Models","created":"2026-04-27","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":"2606.08532","title":"DN-Hypo-Pipeline: An AI-Driven Workflow for Generating Hypotheses using Large Language Models and Scientific Explanations","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2610.04002","title":"Do Language Models Need a Trainable Input Embedding Table? Fixed Minimal Token Codes at 1.7B-Class Scale","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}