{"total":43,"rows":[{"id":"2307.02486","title":"LongNet: Scaling Transformers to 1,000,000,000 Tokens","created":"2023-07-05","cited_by_count":204,"area":null},{"id":"2203.13161","title":"Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generation","created":"2022-03-24","cited_by_count":107,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2203.13357","title":"One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia","created":"2022-03-24","cited_by_count":66,"area":null},{"id":"2110.08118","title":"Few-Shot Bot: Prompt-Based Learning for Dialogue Systems","created":"2021-10-15","cited_by_count":64,"area":null},{"id":"2212.02350","title":"Audio-Driven Co-Speech Gesture Video Generation","created":"2022-12-05","cited_by_count":55,"area":null},{"id":"2403.01255","title":"Automatic Speech Recognition using Advanced Deep Learning Approaches: A survey","created":"2024-03-02","cited_by_count":50,"area":null},{"id":"2303.11607","title":"Transformers in Speech Processing: A Survey","created":"2023-03-21","cited_by_count":39,"area":null},{"id":"2212.09648","title":"NusaCrowd: Open Source Initiative for Indonesian NLP Resources","created":"2022-12-19","cited_by_count":38,"area":null},{"id":"2304.14535","title":"Deep Transfer Learning for Automatic Speech Recognition: Towards Better Generalization","created":"2023-04-27","cited_by_count":28,"area":null},{"id":"2103.15760","title":"Shrinking Bigfoot: Reducing wav2vec 2.0 footprint","created":"2021-03-29","cited_by_count":21,"area":null},{"id":"2305.15099","title":"Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator","created":"2023-05-24","cited_by_count":20,"area":null},{"id":"2201.02419","title":"Automatic Speech Recognition Datasets in Cantonese: A Survey and New Dataset","created":"2022-01-07","cited_by_count":12,"area":null},{"id":"2305.14952","title":"Focus Your Attention (with Adaptive IIR Filters)","created":"2023-05-24","cited_by_count":12,"area":null},{"id":"2201.03804","title":"CI-AVSR: A Cantonese Audio-Visual Speech Dataset for In-car Command Recognition","created":"2022-01-11","cited_by_count":10,"area":null},{"id":"2311.16620","title":"On the Long Range Abilities of Transformers","created":"2023-11-28","cited_by_count":10,"area":null},{"id":"2403.09347","title":"BurstAttention: An Efficient Distributed Attention Framework for Extremely Long Sequences","created":"2024-03-14","cited_by_count":10,"area":null},{"id":"2309.15467","title":"Enabling Resource-efficient AIoT System with Cross-level Optimization: A survey","created":"2023-09-27","cited_by_count":8,"area":null},{"id":"2109.06762","title":"Greenformer: Factorization Toolkit for Efficient Deep Neural Networks","created":"2021-09-14","cited_by_count":7,"area":null},{"id":"2502.20583","title":"LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation","created":"2025-02-27","cited_by_count":7,"area":null},{"id":"2206.14318","title":"Bottleneck Low-rank Transformers for Low-resource Spoken Language Understanding","created":"2022-06-28","cited_by_count":6,"area":null},{"id":"2409.07787","title":"Stable Language Model Pre-training by Reducing Embedding Variability","created":"2024-09-12","cited_by_count":6,"area":null},{"id":"2108.10808","title":"Greenformers: Improving Computation and Memory Efficiency in Transformer Models via Low-Rank Approximation","created":"2021-08-24","cited_by_count":5,"area":null},{"id":"2405.15310","title":"Spectraformer: A Unified Random Feature Framework for Transformer","created":"2024-05-24","cited_by_count":5,"area":null},{"id":"2310.02489","title":"ResidualTransformer: Residual Low-Rank Learning with Weight-Sharing for Transformer Layers","created":"2023-10-03","cited_by_count":4,"area":null},{"id":"2401.08505","title":"Harnessing Orthogonality to Train Low-Rank Neural Networks","created":"2024-01-16","cited_by_count":4,"area":null},{"id":"2409.15104","title":"PecSched: Preemptive and Efficient Cluster Scheduling for LLM Inference","created":"2024-09-23","cited_by_count":4,"area":null},{"id":"2311.03912","title":"FLORA: Fine-grained Low-Rank Architecture Search for Vision Transformer","created":"2023-11-07","cited_by_count":3,"area":null},{"id":"2410.07771","title":"Full-Rank No More: Low-Rank Weight Training for Modern Speech Recognition Models","created":"2024-10-10","cited_by_count":3,"area":null},{"id":"2201.10792","title":"On the Effectiveness of Pinyin-Character Dual-Decoding for End-to-End Mandarin Chinese ASR","created":"2022-01-26","cited_by_count":2,"area":null},{"id":"2408.08567","title":"S$^3$Attention: Improving Long Sequence Attention with Smoothed Skeleton Sketching","created":"2024-08-16","cited_by_count":2,"area":null},{"id":"2507.07954","title":"Input Conditioned Layer Dropping in Speech Foundation Models","created":"2025-07-10","cited_by_count":2,"area":null},{"id":"2512.11411","title":"Sliced ReLU attention: Quasi-linear contextual expressivity via sorting","created":"2025-12-12","cited_by_count":2,"area":null},{"id":"2211.07713","title":"How Long Is Enough? Exploring the Optimal Intervals of Long-Range Clinical Note Language Modeling","created":"2022-10-25","cited_by_count":1,"area":null},{"id":"2306.14517","title":"Cross-Lingual Cross-Age Group Adaptation for Low-Resource Elderly Speech Emotion Recognition","created":"2023-06-26","cited_by_count":1,"area":null},{"id":"2410.20926","title":"Long Sequence Modeling with Attention Tensorization: From Sequence to Tensor Learning","created":"2024-10-28","cited_by_count":1,"area":null},{"id":"2505.16991","title":"An Effective Training Framework for Light-Weight Automatic Speech Recognition Models","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2507.09428","title":"On Information Geometry and Iterative Optimization in Model Compression: Operator Factorization","created":"2025-07-12","cited_by_count":1,"area":null},{"id":"2209.00260","title":"Deep Sparse Conformer for Speech Recognition","created":"2022-09-01","cited_by_count":0,"area":null},{"id":"2303.13072","title":"Beyond Universal Transformer: block reusing with adaptor in Transformer for automatic speech recognition","created":"2023-03-23","cited_by_count":0,"area":null},{"id":"2405.01067","title":"AB-Training: A Communication-Efficient Approach for Distributed Low-Rank Learning","created":"2024-05-02","cited_by_count":0,"area":null},{"id":"2406.08904","title":"AdaPTwin: Low-Cost Adaptive Compression of Product Twins in Transformers","created":"2024-06-13","cited_by_count":0,"area":null},{"id":"2602.21800","title":"An Evaluation of Context Length Extrapolation in Long Code via Positional Embeddings and Efficient Attention","created":"2026-02-25","cited_by_count":0,"area":null}],"next_cursor":null}