{"total":26,"rows":[{"id":"2303.00733","title":"SpeechPrompt v2: Prompt Tuning for Speech Classification Tasks","created":"2023-03-01","cited_by_count":32,"area":null},{"id":"2312.09818","title":"SMILE: Multimodal Dataset for Understanding Laughter in Video with Language Models","created":"2023-12-15","cited_by_count":28,"area":null},{"id":"2410.18882","title":"A Survey of Multimodal Sarcasm Detection","created":"2024-10-24","cited_by_count":19,"area":null},{"id":"2408.13040","title":"SpeechPrompt: Prompting Speech Language Models for Speech Processing Tasks","created":"2024-08-23","cited_by_count":12,"area":null},{"id":"2310.02973","title":"UniverSLU: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions","created":"2023-10-04","cited_by_count":9,"area":null},{"id":"2310.01430","title":"Sarcasm in Sight and Sound: Benchmarking and Expansion to Improve Multimodal Sarcasm Detection","created":"2023-09-29","cited_by_count":7,"area":null},{"id":"2402.03658","title":"Sentiment-enhanced Graph-based Sarcasm Explanation in Dialogue","created":"2024-02-06","cited_by_count":6,"area":null},{"id":"2404.06357","title":"Generalizable Sarcasm Detection Is Just Around The Corner, Of Course!","created":"2024-04-09","cited_by_count":5,"area":null},{"id":"2408.14892","title":"A Functional Trade-off between Prosodic and Semantic Cues in Conveying Sarcasm","created":"2024-08-27","cited_by_count":5,"area":null},{"id":"2506.00955","title":"Leveraging Large Language Models for Sarcastic Speech Annotation in Sarcasm Detection","created":"2025-06-01","cited_by_count":4,"area":null},{"id":"2509.04605","title":"Spoken in Jest, Detected in Earnest: A Systematic Review of Sarcasm Recognition -- Multimodal Fusion, Challenges, and Future Prospects","created":"2025-09-04","cited_by_count":4,"area":null},{"id":"2408.10246","title":"VyAnG-Net: A Novel Multi-Modal Sarcasm Recognition Model by Uncovering Visual, Acoustic and Glossary Features","created":"2024-08-05","cited_by_count":3,"area":null},{"id":"2310.18930","title":"Retrofitting Light-weight Language Models for Emotions using Supervised Contrastive Learning","created":"2023-10-29","cited_by_count":2,"area":null},{"id":"2408.02595","title":"Modelling Visual Semantics via Image Captioning to extract Enhanced Multi-Level Cross-Modal Semantic Incongruity Representation with Attention for Multimodal Sarcasm Detection","created":"2024-08-05","cited_by_count":2,"area":null},{"id":"2508.13028","title":"Integrating Feedback Loss from Bi-modal Sarcasm Detector for Sarcastic Speech Synthesis","created":"2025-08-18","cited_by_count":2,"area":null},{"id":"2510.07096","title":"Modeling Sarcastic Speech: Semantic and Prosodic Cues in a Speech Synthesis Framework","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2510.24178","title":"MuSaG: A Multimodal German Sarcasm Dataset with Full-Modal Annotations","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2606.06168","title":"ProSarc: Prosody-Aware Sarcasm Recognition Framework via Temporal Prosodic Incongruity","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2608.30204","title":"When Models Hear What They Expect: Diagnosing Prosodic Heuristics in Multimodal Sarcasm Detection","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2508.10644","title":"Conditional Information Bottleneck for Multimodal Fusion: Overcoming Shortcut Learning in Sarcasm Detection","created":"2025-08-14","cited_by_count":0,"area":null},{"id":"2603.05275","title":"SarcasmMiner: A Dual-Track Post-Training Framework for Robust Audio-Visual Sarcasm Reasoning","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2605.02447","title":"PC-MNet: Dual-Level Congruity Modeling for Multimodal Sarcasm Detection via Polarity-Modulated Attention","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.18547","title":"VISAFF: Speaker-Centered Visual Affective Feature Learning for Emotion Recognition in Conversation","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.00046","title":"When Jokes Cross the Line: Analyzing Regular Humor and Dark Humor in YouTube Shorts","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2608.21360","title":"OmniAssistBench: Assistant-style Interaction Benchmark for Omni-LLMs","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.26879","title":"Mitigating Strong-Modality Collapse in Multimodal Learning via Inverted Asymmetric Fusion","created":"2026-08-27","cited_by_count":0,"area":null}],"next_cursor":null}