Showing 1–20 of 33 results
/ Date/ Name
Mar 11, 2022Transformer-based Streaming ASR with Cumulative AttentionJun 21, 2024Prompting Whisper for QA-driven Zero-shot End-to-end Spoken Language UnderstandingAug 30, 2018End-to-end Speech Recognition with Adaptive Computation StepsDec 2, 2025Multi-Frequency Federated Learning for Human Activity Recognition Using Head-Worn SensorsJan 7, 2025A Survey on Federated Learning in Human SensingApr 24, 2023Self-regularised Minimum Latency Training for Streaming Transformer-based Speech RecognitionApr 26, 2021Head-synchronous Decoding for Transformer-based Streaming ASRAug 29, 2024WHISMA: A Speech-LLM to Perform Zero-shot Spoken Language UnderstandingFeb 7, 2026Federated Learning with Profile Mapping under Distribution Shifts and DriftsApr 21, 2023Non-autoregressive End-to-end Approaches for Joint Automatic Speech Recognition and Spoken Language UnderstandingNov 27, 2020Transformer-based Online Speech Recognition with Decoder-end Adaptive Computation StepsFeb 18, 2025Towards Robust and Secure Embodied AI: A Survey on Vulnerabilities and AttacksAug 31, 2025PREE: Towards Harmless and Adaptive Fingerprint Editing in Large Language Models via Knowledge Prefix EnhancementJul 8, 2025Conditional Multi-Stage Failure Recovery for Embodied AgentsSep 13, 2024Fingerprint Vector: Enabling Scalable and Efficient Model Fingerprint Transfer via Vector AdditionNov 27, 2025FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution ShiftsAug 8, 2025Latent Fusion Jailbreak: Blending Harmful and Harmless Representations to Elicit Unsafe LLM OutputsFeb 28, 2026SCOUT: Fast Spectral CT Imaging in Ultra LOw-data Regimes via PseUdo-label GeneraTionMar 14, 2026OrigamiBench: An Interactive Environment to Synthesize Flat-Foldable OrigamisJul 29, 2022Multiple-hypothesis RNN-T Loss for Unsupervised Fine-tuning and Self-training of Neural Transducer