Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
CausalFall: Fall prediction wearing motion sensors from a causal perspectiveiFlytek · Expert Systems with ApplicationsNov 6, 2025RGB-T Multi-modal Visual Question Answering in Nighttime and Adverse EnvironmentiFlytek · International Conference on Advanced Sensing, Intelligent Manufacturing (ASIM)Oct 31, 2025Certifying Entanglement Dimensionality by k -Reduction MomentsiFlytek · PRX Quantum1 citationOct 28, 2025PEMD: Pose Estimation on Multiple Domains Including Human and AnimaliFlytek · IEICE Transactions on Fundamentals of Electronics Communications and Computer SciencesOct 28, 2025MiMu: mitigating multiple shortcut learning behavior of transformersiFlytek · Frontiers of Computer ScienceOct 28, 2025Enhancing the Geometric Problem-Solving Ability of Multimodal LLMs via Symbolic-Neural IntegrationiFlytek · ACM International Conference on Multimedia (ACM MM)4 citationsOct 25, 2025Spark LLM and the Scientific Research it empowers: Practice and ThoughtsiFlytek · ACM International Conference on Multimedia (ACM MM)Oct 25, 2025AudioAtlas: A Comprehensive and Balanced Benchmark Towards Movie-Oriented Text-to-Audio GenerationiFlytek · ACM International Conference on Multimedia (ACM MM)Oct 25, 2025MISP-QEKS: A Large-Scale Dataset with Multimodal Cues for Query-by-Example Keyword SpottingiFlytek · ACM International Conference on Multimedia (ACM MM)Oct 25, 2025MMC: Iterative Refinement of VLM Reasoning via MCTS-based Multimodal CritiqueiFlytek · arXiv1 citationOct 24, 2025Language Adaptation Wake Word Spotting via Latent Space from Pre-Trained Speech ModelsiFlytek · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)Oct 22, 2025End-to-End Simultaneous Dysarthric Speech Reconstruction with Frame-Level Adaptor and Multiple Wait-k Knowledge DistillationiFlytek · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)Oct 22, 2025Personalized Bone-Conduction Bandwidth Extension with Speaker CharacteristicsiFlytek · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)Oct 22, 2025DARS: Dysarthria-Aware Rhythm-Style Synthesis for ASR EnhancementiFlytek · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)Oct 22, 2025Latent Swap Joint Diffusion for 2D Long-Form Latent GenerationiFlytek · IEEE/CVF International Conference on Computer Vision (ICCV)Oct 19, 2025Large language models meet text-centric multimodal sentiment analysis: a surveyiFlytek · Science China Information Sciences55 citationsSep 28, 2025From unimodal to multimodal: a framework for generating high-quality multimodal emotional chit-chat dialogueiFlytek · Science China Information SciencesSep 28, 2025Plug-and-play fine grained neural cognitive diagnosis frameworkiFlytek · Engineering Applications of Artificial Intelligence3 citationsSep 23, 2025SimCroP: Radiograph Representation Learning with Similarity-Driven Cross-Granularity Pre-trainingiFlytek · Lecture notes in computer science1 citationSep 19, 2025A selective attention approach for cross-modal target perceptioniFlytek · Scientia Sinica InformationisSep 16, 2025An Enhanced Audio Feature Tailored for Anomalous Sound Detection Based on Pre-trained ModelsiFlytek · Lecture notes in computer science2 citationsSep 9, 2025End-to-End Joint Punctuated and Normalized ASR with a Limited Amount of Punctuated Training DataiFlytek · European Signal Processing Conference (EUSIPCO)1 citationSep 8, 2025FlashRecovery: Fast and Low-Cost Recovery from Failures for Large-Scale Training of LLMsiFlytek · arXiv (Cornell University)Sep 3, 2025MVP-CBM: Multi-layer Visual Preference-enhanced Concept Bottleneck Model for Explainable Medical Image ClassificationiFlytek · International Joint Conference on Artificial Intelligence2 citationsSep 1, 2025Enhancing Table Recognition with Vision LLMs: A Benchmark and Neighbor-Guided Toolchain ReasoneriFlytek · International Joint Conference on Artificial Intelligence2 citationsSep 1, 2025