Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Low-Precision Training of Wan2.1 14B Video Generation Model with HiFloat8 FormatiFlytek · IEEE International Conference on Multimedia and Expo workshopsJul 1EmoInstruct-TTS: Dual-Path Instruction-Guided Emotional Speech SynthesisiFlytek · arXiv (Cornell University)Jun 8Exploring a novel data- and parameter-efficient fine-tuning method for robust face recognitioniFlytek · Pattern RecognitionJun 6Towards higher quality and fewer hallucinations: A multi-agent collaboration framework for LLMsiFlytek · Information Processing & ManagementJun 5SocraticPO: Policy Optimization via Interactive GuidanceiFlytek · arXiv (Cornell University)Jun 3LM-AdvVC: Localized Multi-Granularity Targeted Adversarial Attacks on Voice ConversioniFlytek · International Joint Conference on Neural Networks (IJCNN)Jun 1Research and Practice of Online Course Management System Based on Big Data and Full-Stack TechnologyiFlytek · Industry science and engineering.Jun 1PEARL: Training Socratic Tutors with Pedagogically Aligned Reinforcement LearningiFlytek · arXiv (Cornell University)May 28MACReD: A Multi-Agent Collaborative Reasoning Framework for Reaction Diagram ParsingiFlytek · arXiv (Cornell University)May 27Risk-aware Selective Prompting for Hallucination Mitigation in Large Vision-Language ModelsiFlytek · arXiv (Cornell University)May 27MACReD: A Multi-Agent Collaborative Reasoning Framework for Reaction Diagram ParsingiFlytek · arXiv (Cornell University)May 27Process-Supervised Multi-Step Reasoning with LLMs for Knowledge TaggingiFlytek · International Annual Conference on Complex Systems and Intelligent Science (CSIS-IAC)May 15Reinforcement learning-powered co-optimization: Bridging critic model and multimodal LLM reasoning abilitiesiFlytek · Pattern RecognitionMay 15CIF: A Two-Stage Cognitively-Inspired Framework for Chinese Spelling CorrectioniFlytek · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21SLM-SS: Speech Language Model for Generative Speech SeparationiFlytek · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Integrating Speaker Embeddings and LLM-Derived Semantic Representations for Streaming Speaker DiarizationiFlytek · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Advancing LLM-Based Multi-Channel Multi-Speaker Speech Recognition with Global Cross-Channel Attention and Sentence-Ordered First-In First-Out Serialized Output TrainingiFlytek · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Hierarchical Contrastive Learning with Speech Language Model for Separating Similar SpeakersiFlytek · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21CE-GOCD: Central Entity-Guided Graph Optimization for Community Detection to Augment LLM Scientific Question AnsweringiFlytek · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21EPO: Enhanced Preference Optimization with Multi-Response Data for LLMs via Stochastic SoftmaxiFlytek · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Streaming Speech Recognition with Decoder-Only Large Language Models and Latency OptimizationiFlytek · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21DemoReranker: Enhancing the in-Context Learning Capability of Multi-Modal Large Models VIA Demo RankingiFlytek · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Group Relative Policy Optimization for Text-to-Speech with Large Language ModelsiFlytek · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Improving Anomalous Sound Detection with Attribute-Aware Representation from Domain-Adaptive Pre-TrainingiFlytek · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Rethinking Popularity Bias in Collaborative Filtering via Analytical Vector DecompositioniFlytek · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)2 citationsApr 20