{"total":31,"rows":[{"id":"2305.08455","title":"Document Understanding Dataset and Evaluation (DUDE)","created":"2023-05-15","cited_by_count":135,"area":null},{"id":"2212.10773","title":"MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning","created":"2022-12-21","cited_by_count":109,"area":null},{"id":"2406.13340","title":"SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words","created":"2024-06-19","cited_by_count":68,"area":null},{"id":"2407.11484","title":"The Oscars of AI Theater: A Survey on Role-Playing with Language Models","created":"2024-07-16","cited_by_count":48,"area":null},{"id":"2402.12786","title":"Advancing Large Language Models to Capture Varied Speaking Styles and Respond Properly in Spoken Conversations","created":"2024-02-20","cited_by_count":45,"area":null},{"id":"2402.11975","title":"Compress to Impress: Unleashing the Potential of Compressive Memory in Real-World Long-Term Conversations","created":"2024-02-19","cited_by_count":36,"area":null},{"id":"2212.10525","title":"SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Tasks","created":"2022-12-20","cited_by_count":35,"area":null},{"id":"2305.06154","title":"Alleviating Over-smoothing for Unsupervised Sentence Representation","created":"2023-05-09","cited_by_count":16,"area":null},{"id":"2306.04047","title":"CAVEN: An Embodied Conversational Agent for Efficient Audio-Visual Navigation in Noisy Environments","created":"2023-06-06","cited_by_count":14,"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":"2412.15712","title":"Contrastive Learning for Task-Independent SpeechLLM-Pretraining","created":"2024-12-20","cited_by_count":8,"area":null},{"id":"2601.02391","title":"WearVox: An Egocentric Multichannel Voice Assistant Benchmark for Wearables","created":"2025-12-25","cited_by_count":7,"area":null},{"id":"2302.09302","title":"Bridge the Gap between Language models and Tabular Understanding","created":"2023-02-16","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":"2501.02370","title":"Prepending or Cross-Attention for Speech-to-Text? An Empirical Comparison","created":"2025-01-04","cited_by_count":5,"area":null},{"id":"2505.07705","title":"Codifying Character Logic in Role-Playing","created":"2025-05-12","cited_by_count":5,"area":null},{"id":"2407.11277","title":"Target conversation extraction: Source separation using turn-taking dynamics","created":"2024-07-15","cited_by_count":4,"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":"2407.21066","title":"ELP-Adapters: Parameter Efficient Adapter Tuning for Various Speech Processing Tasks","created":"2024-07-28","cited_by_count":3,"area":null},{"id":"2511.09282","title":"End-to-end Contrastive Language-Speech Pretraining Model For Long-form Spoken Question Answering","created":"2025-11-12","cited_by_count":2,"area":null},{"id":"2205.11008","title":"Calibrate and Refine! A Novel and Agile Framework for ASR-error Robust Intent Detection","created":"2022-05-23","cited_by_count":1,"area":null},{"id":"2206.12759","title":"Low-resource Accent Classification in Geographically-proximate Settings: A Forensic and Sociophonetics Perspective","created":"2022-06-26","cited_by_count":1,"area":null},{"id":"2302.08817","title":"Natural Response Generation for Chinese Reading Comprehension","created":"2023-02-17","cited_by_count":1,"area":null},{"id":"2302.13619","title":"Orca: A Few-shot Benchmark for Chinese Conversational Machine Reading Comprehension","created":"2023-02-27","cited_by_count":1,"area":null},{"id":"2303.06605","title":"Improve Retrieval-based Dialogue System via Syntax-Informed Attention","created":"2023-03-12","cited_by_count":1,"area":null},{"id":"2505.15683","title":"FedSEA-LLaMA: A Secure, Efficient and Adaptive Federated Splitting Framework for Large Language Models","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2509.05716","title":"A Survey of the State-of-the-Art in Conversational Question Answering Systems","created":"2025-09-06","cited_by_count":1,"area":null},{"id":"2511.11473","title":"Proactive Hearing Assistants that Isolate Egocentric Conversations","created":"2025-11-14","cited_by_count":1,"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":"2608.16203","title":"INSPIRE: A Benchmark for Instruction-Aware Speech Retrieval","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.30475","title":"ImageEval 2026: Culturally Grounded Arabic Multimodal Evaluation","created":"2026-08-31","cited_by_count":0,"area":null}],"next_cursor":null}