{"total":105,"rows":[{"id":"2207.07061","title":"Confident Adaptive Language Modeling","created":"2022-07-14","cited_by_count":310,"area":"inference"},{"id":"2211.15089","title":"Continuous diffusion for categorical data","created":"2022-11-28","cited_by_count":214,"area":"diffusion"},{"id":"2205.11491","title":"HyperTree Proof Search for Neural Theorem Proving","created":"2022-05-23","cited_by_count":197,"area":null},{"id":"2203.16487","title":"Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation","created":"2022-03-30","cited_by_count":171,"area":"inference"},{"id":"2302.07863","title":"Speculative Decoding with Big Little Decoder","created":"2023-02-15","cited_by_count":164,"area":"inference"},{"id":"2106.12672","title":"Charformer: Fast Character Transformers via Gradient-based Subword Tokenization","created":"2021-06-23","cited_by_count":160,"area":null},{"id":"2207.06966","title":"Scene Text Recognition with Permuted Autoregressive Sequence Models","created":"2022-07-14","cited_by_count":149,"area":null},{"id":"2305.10427","title":"Accelerating Transformer Inference for Translation via Parallel Decoding","created":"2023-05-17","cited_by_count":124,"area":"inference"},{"id":"2108.08827","title":"ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis","created":"2021-08-19","cited_by_count":122,"area":null},{"id":"2307.15190","title":"f-Divergence Minimization for Sequence-Level Knowledge Distillation","created":"2023-07-27","cited_by_count":114,"area":"distill"},{"id":"2109.07740","title":"Scaling Laws for Neural Machine Translation","created":"2021-09-16","cited_by_count":111,"area":null},{"id":"2312.15234","title":"Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems","created":"2023-12-23","cited_by_count":102,"area":"inference"},{"id":"2103.13076","title":"Finetuning Pretrained Transformers into RNNs","created":"2021-03-24","cited_by_count":96,"area":null},{"id":"2301.08721","title":"Batch Prompting: Efficient Inference with Large Language Model APIs","created":"2023-01-19","cited_by_count":85,"area":null},{"id":"2109.05729","title":"CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation","created":"2021-09-13","cited_by_count":81,"area":null},{"id":"2109.10465","title":"Scalable and Efficient MoE Training for Multitask Multilingual Models","created":"2021-09-22","cited_by_count":76,"area":"moe"},{"id":"2204.09269","title":"A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond","created":"2022-04-20","cited_by_count":64,"area":null},{"id":"2212.08055","title":"UnitY: Two-pass Direct Speech-to-speech Translation with Discrete Units","created":"2022-12-15","cited_by_count":60,"area":null},{"id":"2106.05093","title":"Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation","created":"2021-06-09","cited_by_count":57,"area":null},{"id":"2202.01994","title":"Data Scaling Laws in NMT: The Effect of Noise and Architecture","created":"2022-02-04","cited_by_count":55,"area":null},{"id":"2309.04255","title":"LLMCad: Fast and Scalable On-device Large Language Model Inference","created":"2023-09-08","cited_by_count":45,"area":null},{"id":"2205.07459","title":"Directed Acyclic Transformer for Non-Autoregressive Machine Translation","created":"2022-05-16","cited_by_count":44,"area":null},{"id":"2210.16886","title":"DiffusER: Discrete Diffusion via Edit-based Reconstruction","created":"2022-10-30","cited_by_count":41,"area":"diffusion"},{"id":"2110.07515","title":"Non-Autoregressive Translation with Layer-Wise Prediction and Deep Supervision","created":"2021-10-14","cited_by_count":40,"area":null},{"id":"2307.05908","title":"Predictive Pipelined Decoding: A Compute-Latency Trade-off for Exact LLM Decoding","created":"2023-07-12","cited_by_count":40,"area":null},{"id":"2312.12728","title":"Lookahead: An Inference Acceleration Framework for Large Language Model with Lossless Generation Accuracy","created":"2023-12-20","cited_by_count":37,"area":"inference"},{"id":"2110.02488","title":"ABC: Attention with Bounded-memory Control","created":"2021-10-06","cited_by_count":36,"area":null},{"id":"2310.02410","title":"Mixture of Quantized Experts (MoQE): Complementary Effect of Low-bit Quantization and Robustness","created":"2023-10-03","cited_by_count":34,"area":"moe"},{"id":"2402.01528","title":"Decoding Speculative Decoding","created":"2024-02-02","cited_by_count":34,"area":"inference"},{"id":"2112.04139","title":"Bidimensional Leaderboards: Generate and Evaluate Language Hand in Hand","created":"2021-12-08","cited_by_count":32,"area":null},{"id":"2204.04667","title":"Linear Complexity Randomized Self-attention Mechanism","created":"2022-04-10","cited_by_count":31,"area":null},{"id":"2307.09249","title":"UniTabE: A Universal Pretraining Protocol for Tabular Foundation Model in Data Science","created":"2023-07-18","cited_by_count":29,"area":null},{"id":"2504.06225","title":"Encoder-Decoder Gemma: Improving the Quality-Efficiency Trade-Off via Adaptation","created":"2025-04-08","cited_by_count":28,"area":null},{"id":"2206.05975","title":"On the Learning of Non-Autoregressive Transformers","created":"2022-06-13","cited_by_count":27,"area":null},{"id":"2211.10017","title":"Who Says Elephants Can't Run: Bringing Large Scale MoE Models into Cloud Scale Production","created":"2022-11-18","cited_by_count":27,"area":"moe"},{"id":"2202.00528","title":"Examining Scaling and Transfer of Language Model Architectures for Machine Translation","created":"2022-02-01","cited_by_count":26,"area":null},{"id":"2105.14556","title":"Diversifying Dialog Generation via Adaptive Label Smoothing","created":"2021-05-30","cited_by_count":25,"area":null},{"id":"2502.01567","title":"Latent Thought Models with Variational Bayes Inference-Time Computation","created":"2025-02-03","cited_by_count":25,"area":"lr"},{"id":"2109.06481","title":"AligNART: Non-autoregressive Neural Machine Translation by Jointly Learning to Estimate Alignment and Translate","created":"2021-09-14","cited_by_count":24,"area":null},{"id":"2305.14280","title":"Multilingual Pixel Representations for Translation and Effective Cross-lingual Transfer","created":"2023-05-23","cited_by_count":22,"area":null},{"id":"2202.07959","title":"EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation","created":"2022-02-16","cited_by_count":21,"area":null},{"id":"2109.00055","title":"Sentence Bottleneck Autoencoders from Transformer Language Models","created":"2021-08-31","cited_by_count":19,"area":null},{"id":"2205.14912","title":"E2S2: Encoding-Enhanced Sequence-to-Sequence Pretraining for Language Understanding and Generation","created":"2022-05-30","cited_by_count":19,"area":null},{"id":"2210.03953","title":"Non-Monotonic Latent Alignments for CTC-Based Non-Autoregressive Machine Translation","created":"2022-10-08","cited_by_count":16,"area":null},{"id":"2210.11621","title":"SMaLL-100: Introducing Shallow Multilingual Machine Translation Model for Low-Resource Languages","created":"2022-10-20","cited_by_count":16,"area":null},{"id":"2309.01826","title":"One Wide Feedforward is All You Need","created":"2023-09-04","cited_by_count":15,"area":null},{"id":"2210.05193","title":"Viterbi Decoding of Directed Acyclic Transformer for Non-Autoregressive Machine Translation","created":"2022-10-11","cited_by_count":13,"area":null},{"id":"2305.02665","title":"Learning Language-Specific Layers for Multilingual Machine Translation","created":"2023-05-04","cited_by_count":13,"area":null},{"id":"2205.01966","title":"Non-Autoregressive Machine Translation: It's Not as Fast as it Seems","created":"2022-05-04","cited_by_count":11,"area":null},{"id":"2303.06662","title":"Fuzzy Alignments in Directed Acyclic Graph for Non-Autoregressive Machine Translation","created":"2023-03-12","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":"2204.05424","title":"A Call for Clarity in Beam Search: How It Works and When It Stops","created":"2022-04-11","cited_by_count":10,"area":null},{"id":"2210.07535","title":"AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation","created":"2022-10-14","cited_by_count":10,"area":"moe"},{"id":"2109.04411","title":"Non-autoregressive End-to-end Speech Translation with Parallel Autoregressive Rescoring","created":"2021-09-09","cited_by_count":9,"area":null},{"id":"2111.08634","title":"NVIDIA NeMo Neural Machine Translation Systems for English-German and English-Russian News and Biomedical Tasks at WMT21","created":"2021-11-16","cited_by_count":8,"area":null},{"id":"2112.08152","title":"Faster Nearest Neighbor Machine Translation","created":"2021-12-15","cited_by_count":8,"area":null},{"id":"2210.03999","title":"ngram-OAXE: Phrase-Based Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation","created":"2022-10-08","cited_by_count":8,"area":null},{"id":"2503.05931","title":"Training and Inference Efficiency of Encoder-Decoder Speech Models","created":"2025-03-07","cited_by_count":8,"area":null},{"id":"2205.11277","title":"When does Parameter-Efficient Transfer Learning Work for Machine Translation?","created":"2022-05-23","cited_by_count":7,"area":null},{"id":"2212.09553","title":"Mu$^{2}$SLAM: Multitask, Multilingual Speech and Language Models","created":"2022-12-19","cited_by_count":7,"area":null},{"id":"2310.10054","title":"NASH: A Simple Unified Framework of Structured Pruning for Accelerating Encoder-Decoder Language Models","created":"2023-10-16","cited_by_count":7,"area":null},{"id":"2209.05861","title":"Unified Generative & Dense Retrieval for Query Rewriting in Sponsored Search","created":"2022-09-13","cited_by_count":6,"area":null},{"id":"2407.21046","title":"Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines","created":"2024-07-22","cited_by_count":6,"area":null},{"id":"2205.10577","title":"Non-Autoregressive Neural Machine Translation: A Call for Clarity","created":"2022-05-21","cited_by_count":5,"area":null},{"id":"2210.06020","title":"Integrating Translation Memories into Non-Autoregressive Machine Translation","created":"2022-10-12","cited_by_count":5,"area":null},{"id":"2303.07457","title":"AMOM: Adaptive Masking over Masking for Conditional Masked Language Model","created":"2023-03-13","cited_by_count":5,"area":null},{"id":"2304.01016","title":"Quick Dense Retrievers Consume KALE: Post Training Kullback Leibler Alignment of Embeddings for Asymmetrical dual encoders","created":"2023-03-31","cited_by_count":5,"area":null},{"id":"2311.08263","title":"Fast Chain-of-Thought: A Glance of Future from Parallel Decoding Leads to Answers Faster","created":"2023-11-14","cited_by_count":5,"area":"lr"},{"id":"2403.01479","title":"Align-to-Distill: Trainable Attention Alignment for Knowledge Distillation in Neural Machine Translation","created":"2024-03-03","cited_by_count":5,"area":"distill"},{"id":"2409.17673","title":"Cross-lingual Human-Preference Alignment for Neural Machine Translation with Direct Quality Optimization","created":"2024-09-26","cited_by_count":5,"area":"alignment"},{"id":"2205.09273","title":"Twist Decoding: Diverse Generators Guide Each Other","created":"2022-05-19","cited_by_count":4,"area":null},{"id":"2206.14982","title":"Building Multilingual Machine Translation Systems That Serve Arbitrary X-Y Translations","created":"2022-06-30","cited_by_count":4,"area":null},{"id":"2412.16719","title":"Lillama: Large Language Models Compression via Low-Rank Feature Distillation","created":"2024-12-21","cited_by_count":4,"area":"distill"},{"id":"2506.06042","title":"SDS-Net: Shallow-Deep Synergism-detection Network for infrared small target detection","created":"2025-06-06","cited_by_count":4,"area":null},{"id":"2510.08599","title":"BaldWhisper: Faster Whisper with Head Shearing and Layer Merging","created":"2025-10-06","cited_by_count":4,"area":null},{"id":"2205.06618","title":"The Devil is in the Details: On the Pitfalls of Vocabulary Selection in Neural Machine Translation","created":"2022-05-13","cited_by_count":3,"area":null},{"id":"2212.10240","title":"Diffusion Glancing Transformer for Parallel Sequence to Sequence Learning","created":"2022-12-20","cited_by_count":3,"area":null},{"id":"2210.06709","title":"Categorizing Semantic Representations for Neural Machine Translation","created":"2022-10-13","cited_by_count":2,"area":null},{"id":"2210.12582","title":"Language Model Pre-Training with Sparse Latent Typing","created":"2022-10-23","cited_by_count":2,"area":null},{"id":"2303.17910","title":"Selective Knowledge Distillation for Non-Autoregressive Neural Machine Translation","created":"2023-03-31","cited_by_count":2,"area":"distill"},{"id":"2305.16155","title":"Revisiting Non-Autoregressive Translation at Scale","created":"2023-05-25","cited_by_count":2,"area":null},{"id":"2307.10799","title":"Layer-wise Representation Fusion for Compositional Generalization","created":"2023-07-20","cited_by_count":2,"area":null},{"id":"2501.17332","title":"Compact Neural TTS Voices for Accessibility","created":"2025-01-28","cited_by_count":2,"area":null},{"id":"2505.13254","title":"HeteroSpec: Leveraging Contextual Heterogeneity for Efficient Speculative Decoding","created":"2025-05-19","cited_by_count":2,"area":"inference"},{"id":"2505.16502","title":"Recursive Offloading for LLM Serving in Multi-tier Networks","created":"2025-05-22","cited_by_count":2,"area":"inference"},{"id":"2602.15845","title":"KD4MT: A Survey of Knowledge Distillation for Machine Translation","created":"2026-01-22","cited_by_count":2,"area":"distill"},{"id":"2112.08570","title":"Can Multilinguality benefit Non-autoregressive Machine Translation?","created":"2021-12-16","cited_by_count":1,"area":null},{"id":"2205.15744","title":"EMS: Efficient and Effective Massively Multilingual Sentence Embedding Learning","created":"2022-05-31","cited_by_count":1,"area":null},{"id":"2208.05852","title":"Language Tokens: A Frustratingly Simple Approach Improves Zero-Shot Performance of Multilingual Translation","created":"2022-08-11","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":"2211.13194","title":"Indian Commercial Truck License Plate Detection and Recognition for Weighbridge Automation","created":"2022-11-23","cited_by_count":1,"area":null},{"id":"2303.07665","title":"RenewNAT: Renewing Potential Translation for Non-Autoregressive Transformer","created":"2023-03-14","cited_by_count":1,"area":null},{"id":"2304.02721","title":"To Asymmetry and Beyond: Structured Pruning of Sequence to Sequence Models for Improved Inference Efficiency","created":"2023-04-05","cited_by_count":1,"area":null},{"id":"2309.10898","title":"RedPenNet for Grammatical Error Correction: Outputs to Tokens, Attentions to Spans","created":"2023-09-19","cited_by_count":1,"area":null},{"id":"2310.19322","title":"Progressive Neural Network for Multi-Horizon Time Series Forecasting","created":"2023-10-30","cited_by_count":1,"area":null},{"id":"2502.04537","title":"Multilingual Non-Autoregressive Machine Translation without Knowledge Distillation","created":"2025-02-06","cited_by_count":1,"area":"distill"},{"id":"2206.02999","title":"DiMS: Distilling Multiple Steps of Iterative Non-Autoregressive Transformers for Machine Translation","created":"2022-06-07","cited_by_count":0,"area":null},{"id":"2311.18200","title":"INarIG: Iterative Non-autoregressive Instruct Generation Model For Word-Level Auto Completion","created":"2023-11-30","cited_by_count":0,"area":null},{"id":"2312.00912","title":"Quick Back-Translation for Unsupervised Machine Translation","created":"2023-12-01","cited_by_count":0,"area":null},{"id":"2412.02101","title":"Improving Language Transfer Capability of Decoder-only Architecture in Multilingual Neural Machine Translation","created":"2024-12-03","cited_by_count":0,"area":null}],"next_cursor":"100"}