{"total":94,"rows":[{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057,"area":null},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780,"area":null},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629,"area":null},{"id":"2109.00486","title":"Survey of Low-Resource Machine Translation","created":"2021-09-01","cited_by_count":92,"area":null},{"id":"2305.19000","title":"Independent Component Alignment for Multi-Task Learning","created":"2023-05-30","cited_by_count":70,"area":null},{"id":"2109.09138","title":"Multi-Task Learning in Natural Language Processing: An Overview","created":"2021-09-19","cited_by_count":62,"area":null},{"id":"2303.01911","title":"Investigating the Translation Performance of a Large Multilingual Language Model: the Case of BLOOM","created":"2023-03-03","cited_by_count":59,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2204.03508","title":"A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methods","created":"2022-04-07","cited_by_count":42,"area":null},{"id":"2203.00633","title":"Transformer Grammars: Augmenting Transformer Language Models with Syntactic Inductive Biases at Scale","created":"2022-03-01","cited_by_count":41,"area":null},{"id":"2109.12575","title":"Paradigm Shift in Natural Language Processing","created":"2021-09-26","cited_by_count":39,"area":null},{"id":"2305.08264","title":"MatSci-NLP: Evaluating Scientific Language Models on Materials Science Language Tasks Using Text-to-Schema Modeling","created":"2023-05-14","cited_by_count":35,"area":null},{"id":"2104.02156","title":"Unified Detection of Digital and Physical Face Attacks","created":"2021-04-05","cited_by_count":31,"area":null},{"id":"2302.09650","title":"Scaling Laws for Multilingual Neural Machine Translation","created":"2023-02-19","cited_by_count":27,"area":null},{"id":"2406.18676","title":"Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation","created":"2024-06-26","cited_by_count":27,"area":"rag"},{"id":"2302.03328","title":"Multi-Task Recommendations with Reinforcement Learning","created":"2023-02-07","cited_by_count":26,"area":null},{"id":"2107.09106","title":"Separating Skills and Concepts for Novel Visual Question Answering","created":"2021-07-19","cited_by_count":24,"area":null},{"id":"2106.09063","title":"Specializing Multilingual Language Models: An Empirical Study","created":"2021-06-16","cited_by_count":21,"area":null},{"id":"2402.17016","title":"Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddings","created":"2024-02-26","cited_by_count":21,"area":null},{"id":"2403.09323","title":"E2E-MFD: Towards End-to-End Synchronous Multimodal Fusion Detection","created":"2024-03-14","cited_by_count":21,"area":null},{"id":"2104.07554","title":"Zero-Shot Cross-lingual Semantic Parsing","created":"2021-04-15","cited_by_count":19,"area":null},{"id":"2111.01338","title":"Federated Split Vision Transformer for COVID-19 CXR Diagnosis using Task-Agnostic Training","created":"2021-11-02","cited_by_count":17,"area":null},{"id":"2407.14032","title":"Semantic-CC: Boosting Remote Sensing Image Change Captioning via Foundational Knowledge and Semantic Guidance","created":"2024-07-19","cited_by_count":17,"area":null},{"id":"2412.18495","title":"How \"Real\" is Your Real-Time Simultaneous Speech-to-Text Translation System?","created":"2024-12-24","cited_by_count":17,"area":null},{"id":"2107.04239","title":"A Survey on Low-Resource Neural Machine Translation","created":"2021-07-09","cited_by_count":16,"area":null},{"id":"2110.06997","title":"Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits","created":"2021-10-13","cited_by_count":16,"area":null},{"id":"2104.07639","title":"Robust Optimization for Multilingual Translation with Imbalanced Data","created":"2021-04-15","cited_by_count":15,"area":null},{"id":"2605.27115","title":"Counteraction-Aware Multi-Teacher On-Policy Distillation for General Capability Recovery with Domain Preservation","created":"2026-05-26","cited_by_count":15,"area":"distill"},{"id":"2110.07804","title":"Alternative Input Signals Ease Transfer in Multilingual Machine Translation","created":"2021-10-15","cited_by_count":14,"area":null},{"id":"2103.17151","title":"Divide and Rule: Effective Pre-Training for Context-Aware Multi-Encoder Translation Models","created":"2021-03-31","cited_by_count":12,"area":null},{"id":"2106.05544","title":"CogAlign: Learning to Align Textual Neural Representations to Cognitive Language Processing Signals","created":"2021-06-10","cited_by_count":11,"area":null},{"id":"2101.11287","title":"Language Modelling as a Multi-Task Problem","created":"2021-01-27","cited_by_count":10,"area":null},{"id":"2204.04637","title":"UniDU: Towards A Unified Generative Dialogue Understanding Framework","created":"2022-04-10","cited_by_count":9,"area":null},{"id":"2306.09478","title":"Understanding and Mitigating Extrapolation Failures in Physics-Informed Neural Networks","created":"2023-06-15","cited_by_count":9,"area":null},{"id":"2404.18470","title":"ECC Analyzer: Extract Trading Signal from Earnings Conference Calls using Large Language Model for Stock Performance Prediction","created":"2024-04-29","cited_by_count":9,"area":null},{"id":"2502.06244","title":"PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2104.00366","title":"Low-Resource Neural Machine Translation for Southern African Languages","created":"2021-04-01","cited_by_count":7,"area":null},{"id":"2210.13388","title":"Focused Concatenation for Context-Aware Neural Machine Translation","created":"2022-10-24","cited_by_count":7,"area":null},{"id":"2302.11466","title":"Advancements in Federated Learning: Models, Methods, and Privacy","created":"2023-02-22","cited_by_count":7,"area":null},{"id":"2101.09645","title":"Multi-Task Time Series Forecasting With Shared Attention","created":"2021-01-24","cited_by_count":6,"area":null},{"id":"2102.08065","title":"Learning to Recognize Actions on Objects in Egocentric Video with Attention Dictionaries","created":"2021-02-16","cited_by_count":6,"area":null},{"id":"2204.06625","title":"CAMERO: Consistency Regularized Ensemble of Perturbed Language Models with Weight Sharing","created":"2022-04-13","cited_by_count":6,"area":null},{"id":"2210.12865","title":"Knowledge Transfer from Answer Ranking to Answer Generation","created":"2022-10-23","cited_by_count":6,"area":null},{"id":"2302.10175","title":"Spatio-Temporal Momentum: Jointly Learning Time-Series and Cross-Sectional Strategies","created":"2023-02-20","cited_by_count":6,"area":null},{"id":"2305.06361","title":"Efficient Training of Multi-task Neural Solver for Combinatorial Optimization","created":"2023-05-10","cited_by_count":6,"area":null},{"id":"2404.07452","title":"RiskLabs: Predicting Financial Risk Using Large Language Model based on Multimodal and Multi-Sources Data","created":"2024-04-11","cited_by_count":6,"area":null},{"id":"2103.15361","title":"Embedding API Dependency Graph for Neural Code Generation","created":"2021-03-29","cited_by_count":5,"area":null},{"id":"2110.07936","title":"Unifying Cross-lingual Summarization and Machine Translation with Compression Rate","created":"2021-10-15","cited_by_count":5,"area":null},{"id":"2204.08226","title":"Empirical Evaluation and Theoretical Analysis for Representation Learning: A Survey","created":"2022-04-18","cited_by_count":5,"area":null},{"id":"2210.11807","title":"Is Encoder-Decoder Redundant for Neural Machine Translation?","created":"2022-10-21","cited_by_count":5,"area":null},{"id":"2305.07393","title":"Prompt Learning to Mitigate Catastrophic Forgetting in Cross-lingual Transfer for Open-domain Dialogue Generation","created":"2023-05-12","cited_by_count":4,"area":null},{"id":"2310.16241","title":"Task Grouping for Automated Multi-Task Machine Learning via Task Affinity Prediction","created":"2023-10-24","cited_by_count":4,"area":null},{"id":"2407.03076","title":"A Case Study on Context-Aware Neural Machine Translation with Multi-Task Learning","created":"2024-07-03","cited_by_count":4,"area":null},{"id":"2106.03484","title":"BERTGEN: Multi-task Generation through BERT","created":"2021-06-07","cited_by_count":3,"area":null},{"id":"2106.04476","title":"One Semantic Parser to Parse Them All: Sequence to Sequence Multi-Task Learning on Semantic Parsing Datasets","created":"2021-06-08","cited_by_count":3,"area":null},{"id":"2212.08992","title":"PoE: a Panel of Experts for Generalized Automatic Dialogue Assessment","created":"2022-12-18","cited_by_count":3,"area":null},{"id":"2301.03416","title":"ERNIE 3.0 Tiny: Frustratingly Simple Method to Improve Task-Agnostic Distillation Generalization","created":"2023-01-09","cited_by_count":3,"area":"distill"},{"id":"2305.04876","title":"Explainable Parallel RCNN with Novel Feature Representation for Time Series Forecasting","created":"2023-05-08","cited_by_count":3,"area":null},{"id":"2305.17652","title":"ConaCLIP: Exploring Distillation of Fully-Connected Knowledge Interaction Graph for Lightweight Text-Image Retrieval","created":"2023-05-28","cited_by_count":3,"area":null},{"id":"2405.14222","title":"Rate-Adaptive Quantization: A Multi-Rate Codebook Adaptation for Vector Quantization-based Generative Models","created":"2024-05-23","cited_by_count":3,"area":null},{"id":"2501.16050","title":"Skeleton-Guided-Translation: A Benchmarking Framework for Code Repository Translation with Fine-Grained Quality Evaluation","created":"2025-01-27","cited_by_count":3,"area":null},{"id":"2105.09404","title":"Computational Morphology with Neural Network Approaches","created":"2021-05-19","cited_by_count":2,"area":null},{"id":"2107.11435","title":"HierMUD: Hierarchical Multi-task Unsupervised Domain Adaptation between Bridges for Drive-by Damage Diagnosis","created":"2021-07-23","cited_by_count":2,"area":null},{"id":"2201.02009","title":"PAEG: Phrase-level Adversarial Example Generation for Neural Machine Translation","created":"2022-01-06","cited_by_count":2,"area":null},{"id":"2310.15612","title":"Machine Translation for Nko: Tools, Corpora and Baseline Results","created":"2023-10-24","cited_by_count":2,"area":null},{"id":"2404.19505","title":"Context-Aware Machine Translation with Source Coreference Explanation","created":"2024-04-30","cited_by_count":2,"area":null},{"id":"2103.05951","title":"Self-Learning for Zero Shot Neural Machine Translation","created":"2021-03-10","cited_by_count":1,"area":null},{"id":"2105.03432","title":"Generalising Multilingual Concept-to-Text NLG with Language Agnostic Delexicalisation","created":"2021-05-07","cited_by_count":1,"area":null},{"id":"2105.14214","title":"Predictive Representation Learning for Language Modeling","created":"2021-05-29","cited_by_count":1,"area":null},{"id":"2109.09354","title":"CUNI systems for WMT21: Multilingual Low-Resource Translation for Indo-European Languages Shared Task","created":"2021-09-20","cited_by_count":1,"area":null},{"id":"2203.03624","title":"FCNet: A Convolutional Neural Network for Arbitrary-Length Exposure Estimation","created":"2022-03-05","cited_by_count":1,"area":null},{"id":"2203.15860","title":"Visualizing the Relationship Between Encoded Linguistic Information and Task Performance","created":"2022-03-29","cited_by_count":1,"area":null},{"id":"2209.01530","title":"Informative Language Representation Learning for Massively Multilingual Neural Machine Translation","created":"2022-09-04","cited_by_count":1,"area":null},{"id":"2301.02275","title":"Language as a Latent Sequence: deep latent variable models for semi-supervised paraphrase generation","created":"2023-01-05","cited_by_count":1,"area":null},{"id":"2308.06063","title":"A Case Study on Context Encoding in Multi-Encoder based Document-Level Neural Machine Translation","created":"2023-08-11","cited_by_count":1,"area":null},{"id":"2311.14835","title":"Weak Alignment Supervision from Hybrid Model Improves End-to-end ASR","created":"2023-11-24","cited_by_count":1,"area":null},{"id":"2401.06321","title":"Multi-Task Learning for Front-End Text Processing in TTS","created":"2024-01-12","cited_by_count":1,"area":null},{"id":"2408.02128","title":"Table Transformers for Imputing Textual Attributes","created":"2024-08-04","cited_by_count":1,"area":null},{"id":"2503.18023","title":"Regularization of ML models for Earth systems by using longer model timesteps","created":"2025-03-23","cited_by_count":1,"area":null},{"id":"2505.07783","title":"Relative Overfitting and Accept-Reject Framework","created":"2025-05-12","cited_by_count":1,"area":null},{"id":"2110.00712","title":"Improving Zero-shot Multilingual Neural Machine Translation for Low-Resource Languages","created":"2021-10-02","cited_by_count":0,"area":null},{"id":"2112.01742","title":"Multitask Finetuning for Improving Neural Machine Translation in Indian Languages","created":"2021-12-03","cited_by_count":0,"area":null},{"id":"2201.09199","title":"Deep Learning on Attributed Sequences","created":"2022-01-23","cited_by_count":0,"area":null},{"id":"2209.13444","title":"Design Perspectives of Multitask Deep Learning Models and Applications","created":"2022-09-27","cited_by_count":0,"area":null},{"id":"2210.04001","title":"Don't Waste Data: Transfer Learning to Leverage All Data for Machine-Learnt Climate Model Emulation","created":"2022-10-08","cited_by_count":0,"area":null},{"id":"2303.15072","title":"Exposing the Functionalities of Neurons for Gated Recurrent Unit Based Sequence-to-Sequence Model","created":"2023-03-27","cited_by_count":0,"area":null},{"id":"2311.05075","title":"Mental Health Diagnosis in the Digital Age: Harnessing Sentiment Analysis on Social Media Platforms upon Ultra-Sparse Feature Content","created":"2023-11-09","cited_by_count":0,"area":null},{"id":"2402.06224","title":"Adaptive multi-gradient methods for quasiconvex vector optimization and applications to multi-task learning","created":"2024-02-09","cited_by_count":0,"area":null},{"id":"2402.15594","title":"Alternating Weak Triphone/BPE Alignment Supervision from Hybrid Model Improves End-to-End ASR","created":"2024-02-23","cited_by_count":0,"area":null},{"id":"2509.08470","title":"Joint Learning using Mixture-of-Expert-Based Representation for Speech Enhancement and Robust Emotion Recognition","created":"2025-09-10","cited_by_count":0,"area":"moe"},{"id":"2510.05175","title":"Exact Causal Attention with 10% Fewer Operations","created":"2025-10-05","cited_by_count":0,"area":null},{"id":"2510.08580","title":"LadderSym: A Multimodal Interleaved Transformer for Music Practice Error Detection","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2602.18591","title":"Ensemble Prediction of Task Affinity for Efficient Multi-Task Learning","created":"2026-02-20","cited_by_count":0,"area":null},{"id":"2609.29131","title":"Tag-Aware Structured Text Translation: Towards a Systematic Understanding","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}