{"total":20,"rows":[{"id":"2207.00032","title":"DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale","created":"2022-06-30","cited_by_count":407,"area":null},{"id":"2302.09210","title":"How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation","created":"2023-02-18","cited_by_count":348,"area":null},{"id":"2202.01169","title":"Unified Scaling Laws for Routed Language Models","created":"2022-02-02","cited_by_count":253,"area":null},{"id":"2309.04662","title":"MADLAD-400: A Multilingual And Document-Level Large Audited Dataset","created":"2023-09-09","cited_by_count":181,"area":null},{"id":"2110.12894","title":"The Efficiency Misnomer","created":"2021-10-25","cited_by_count":98,"area":null},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2212.09811","title":"Memory-efficient NLLB-200: Language-specific Expert Pruning of a Massively Multilingual Machine Translation Model","created":"2022-12-19","cited_by_count":36,"area":null},{"id":"2401.16677","title":"T3: Transparent Tracking & Triggering for Fine-grained Overlap of Compute & Collectives","created":"2024-01-30","cited_by_count":16,"area":null},{"id":"2210.11803","title":"Revisiting Checkpoint Averaging for Neural Machine Translation","created":"2022-10-21","cited_by_count":13,"area":null},{"id":"2401.08429","title":"Machine Translation with Large Language Models: Prompt Engineering for Persian, English, and Russian Directions","created":"2024-01-16","cited_by_count":12,"area":null},{"id":"2502.17771","title":"Sample Selection via Contrastive Fragmentation for Noisy Label Regression","created":"2025-02-25","cited_by_count":4,"area":null},{"id":"2208.05596","title":"Finding Reusable Machine Learning Components to Build Programming Language Processing Pipelines","created":"2022-08-11","cited_by_count":3,"area":null},{"id":"2304.01005","title":"Federated Learning Based Multilingual Emoji Prediction In Clean and Attack Scenarios","created":"2023-03-30","cited_by_count":3,"area":null},{"id":"2302.05008","title":"Language-Aware Multilingual Machine Translation with Self-Supervised Learning","created":"2023-02-10","cited_by_count":2,"area":null},{"id":"2408.10536","title":"Synergistic Approach for Simultaneous Optimization of Monolingual, Cross-lingual, and Multilingual Information Retrieval","created":"2024-08-20","cited_by_count":2,"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":"2407.19965","title":"Simply Trainable Nearest Neighbour Machine Translation with GPU Inference","created":"2024-07-29","cited_by_count":0,"area":null},{"id":"2508.06524","title":"CarbonScaling: Extending Neural Scaling Laws for Carbon Footprint in Large Language Models","created":"2025-08-02","cited_by_count":0,"area":null},{"id":"2508.09228","title":"Objective Soups: Multilingual Multi-Task Modeling for Speech Processing","created":"2025-08-12","cited_by_count":0,"area":null},{"id":"2511.13040","title":"How Good is BLI as an Alignment Measure: A Study in Word Embedding Paradigm","created":"2025-11-17","cited_by_count":0,"area":null}],"next_cursor":null}