Showing 1–18 of 18 results
/ Date/ Name
Aug 15, 2023Better Zero-Shot Reasoning with Role-Play PromptingMay 8, 2023PromptRank: Unsupervised Keyphrase Extraction Using PromptJul 12, 2024Self-Prompt Tuning: Enable Autonomous Role-Playing in LLMsJan 3, 2025SDPO: Segment-Level Direct Preference Optimization for Social AgentsJul 12, 2024Enhancing Emotion Recognition in Incomplete Data: A Novel Cross-Modal Alignment, Reconstruction, and Refinement FrameworkSep 18, 2025Mind the Gap: Data Rewriting for Stable Off-Policy Supervised Fine-TuningJul 24, 2025DIFFA: Large Language Diffusion Models Can Listen and UnderstandMay 29, 2025EmotionTalk: An Interactive Chinese Multimodal Emotion Dataset With Rich AnnotationsSep 27, 2024ChildMandarin: A Comprehensive Mandarin Speech Dataset for Young Children Aged 3-5Aug 6, 2025RealTalk-CN: A Realistic Chinese Speech-Text Dialogue Benchmark With Cross-Modal Interaction AnalysisJan 14, 2026STEP3-VL-10B Technical ReportSep 23, 2025MECap-R1: Emotion-aware Policy with Reinforcement Learning for Multimodal Emotion CaptioningJul 26, 2024Enhancing Dysarthric Speech Recognition for Unseen Speakers via Prototype-Based AdaptationFeb 26, 2025CS-Dialogue: A 104-Hour Dataset of Spontaneous Mandarin-English Code-Switching Dialogues for Speech RecognitionFeb 18, 2025EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via Reinforcement LearningSep 18, 2024M2R-Whisper: Multi-stage and Multi-scale Retrieval Augmentation for Enhancing WhisperSep 23, 2025MAPEX: A Multi-Agent Pipeline for Keyphrase ExtractionFeb 11, 2026Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters