{"total":30,"rows":[{"id":"2107.12708","title":"QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension","created":"2021-07-27","cited_by_count":91,"area":null},{"id":"2108.06227","title":"SimCVD: Simple Contrastive Voxel-Wise Representation Distillation for Semi-Supervised Medical Image Segmentation","created":"2021-08-13","cited_by_count":86,"area":null},{"id":"2105.07059","title":"Momentum Contrastive Voxel-wise Representation Learning for Semi-supervised Volumetric Medical Image Segmentation","created":"2021-05-14","cited_by_count":49,"area":null},{"id":"2111.04318","title":"Auto-Encoding Knowledge Graph for Unsupervised Medical Report Generation","created":"2021-11-08","cited_by_count":47,"area":null},{"id":"2109.03381","title":"Self-supervised Contrastive Cross-Modality Representation Learning for Spoken Question Answering","created":"2021-09-08","cited_by_count":39,"area":null},{"id":"2109.12072","title":"SD-QA: Spoken Dialectal Question Answering for the Real World","created":"2021-09-24","cited_by_count":38,"area":null},{"id":"2204.14272","title":"End-to-end Spoken Conversational Question Answering: Task, Dataset and Model","created":"2022-04-29","cited_by_count":37,"area":null},{"id":"2503.10084","title":"Why Prompt Design Matters and Works: A Complexity Analysis of Prompt Search Space in LLMs","created":"2025-03-13","cited_by_count":31,"area":null},{"id":"2106.02182","title":"Self-supervised Dialogue Learning for Spoken Conversational Question Answering","created":"2021-06-04","cited_by_count":28,"area":null},{"id":"2106.04016","title":"Disfl-QA: A Benchmark Dataset for Understanding Disfluencies in Question Answering","created":"2021-06-08","cited_by_count":20,"area":null},{"id":"2304.13689","title":"HeySQuAD: A Spoken Question Answering Dataset","created":"2023-04-26","cited_by_count":16,"area":null},{"id":"2112.05842","title":"Revisiting the Boundary between ASR and NLU in the Age of Conversational Dialog Systems","created":"2021-12-10","cited_by_count":15,"area":null},{"id":"2203.04911","title":"DUAL: Discrete Spoken Unit Adaptive Learning for Textless Spoken Question Answering","created":"2022-03-09","cited_by_count":15,"area":null},{"id":"2211.12148","title":"Aligning Source Visual and Target Language Domains for Unpaired Video Captioning","created":"2022-11-22","cited_by_count":14,"area":null},{"id":"2308.10390","title":"LibriSQA: A Novel Dataset and Framework for Spoken Question Answering with Large Language Models","created":"2023-08-20","cited_by_count":14,"area":null},{"id":"2112.04735","title":"From Good to Best: Two-Stage Training for Cross-lingual Machine Reading Comprehension","created":"2021-12-09","cited_by_count":10,"area":null},{"id":"2111.00278","title":"A Decentralized Reinforcement Learning Framework for Efficient Passage of Emergency Vehicles","created":"2021-10-30","cited_by_count":9,"area":null},{"id":"2206.13441","title":"EMVLight: a Multi-agent Reinforcement Learning Framework for an Emergency Vehicle Decentralized Routing and Traffic Signal Control System","created":"2022-06-27","cited_by_count":9,"area":null},{"id":"2110.15327","title":"MEGAN: Memory Enhanced Graph Attention Network for Space-Time Video Super-Resolution","created":"2021-10-28","cited_by_count":8,"area":null},{"id":"2505.19163","title":"SpokenNativQA: Multilingual Everyday Spoken Queries for LLMs","created":"2025-05-25","cited_by_count":8,"area":null},{"id":"2204.05210","title":"Bridging the Gap between Language Models and Cross-Lingual Sequence Labeling","created":"2022-04-11","cited_by_count":7,"area":null},{"id":"2206.05311","title":"Graph-in-Graph Network for Automatic Gene Ontology Description Generation","created":"2022-06-10","cited_by_count":5,"area":null},{"id":"2209.00277","title":"Video-Guided Curriculum Learning for Spoken Video Grounding","created":"2022-09-01","cited_by_count":5,"area":null},{"id":"2410.20163","title":"UniHGKR: Unified Instruction-aware Heterogeneous Knowledge Retrievers","created":"2024-10-26","cited_by_count":5,"area":null},{"id":"2401.17604","title":"Computation and Parameter Efficient Multi-Modal Fusion Transformer for Cued Speech Recognition","created":"2024-01-31","cited_by_count":3,"area":null},{"id":"2406.15119","title":"Breaking Resource Barriers in Speech Emotion Recognition via Data Distillation","created":"2024-06-21","cited_by_count":1,"area":null},{"id":"2109.05429","title":"EMVLight: A Decentralized Reinforcement Learning Framework for Efficient Passage of Emergency Vehicles","created":"2021-09-12","cited_by_count":0,"area":null},{"id":"2208.08750","title":"Exploring and Exploiting Multi-Granularity Representations for Machine Reading Comprehension","created":"2022-08-18","cited_by_count":0,"area":null},{"id":"2607.02763","title":"LuxSQA: Ask Me in Luxembourgish with TTS-Augmented Spoken Question Answering","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.22872","title":"Better Retrieval, Worse Robustness: How Multi-hop RAG Amplifies Upstream ASR Errors","created":"2026-08-24","cited_by_count":0,"area":null}],"next_cursor":null}