Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
VisualPRM: An Effective Process Reward Model for Multimodal ReasoningSenseTime · arXiv (Cornell University)157 citationsMar 13, 2025LHM: Large Animatable Human Reconstruction Model from a Single Image in SecondsAlibaba · arXiv (Cornell University)37 citationsMar 13, 2025Structured Preconditioners in Adaptive Optimization: A Unified AnalysisAlphabet · arXiv (Cornell University)26 citationsMar 13, 2025KV-Distill: Nearly Lossless Learnable Context Compression for LLMsMicrosoft · arXiv (Cornell University)17 citationsMar 13, 2025Gaussian DP for Reporting Differential Privacy Guarantees in Machine LearningGoogle DeepMind · arXiv (Cornell University)16 citationsMar 13, 2025What Constitutes a Less Discriminatory Algorithm?Microsoft · arXiv10 citationsMar 13, 2025Spherical dimensionAlphabet · arXiv (Cornell University)6 citationsMar 13, 2025Towards Understanding Graphical Perception in Large Multimodal ModelsMicrosoft · arXiv (Cornell University)5 citationsMar 13, 2025Large-Small Model Collaboration for Enhancing Edge-Deployed Small ModelsAlibaba · arXiv (Cornell University)Mar 13, 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement LearningAlphabet · arXiv (Cornell University)1,445 citationsMar 12, 2025SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model InterpretabilityAnthropic · arXiv (Cornell University)90 citationsMar 12, 2025Large Language Models are Strong Audio-Visual Speech Recognition LearnersMeta · IEEE International Conference on Acoustics Speech and Signal Processing45 citationsMar 12, 2025Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning DataNVIDIA · IEEE International Conference on Acoustics Speech and Signal Processing34 citationsMar 12, 20253D-Speaker-Toolkit: An Open-Source Toolkit for Multimodal Speaker Verification and DiarizationAlibaba · IEEE International Conference on Acoustics Speech and Signal Processing32 citationsMar 12, 2025Boosting Large Language Model for Speech Synthesis: An Empirical StudyMicrosoft · IEEE International Conference on Acoustics Speech and Signal Processing28 citationsMar 12, 2025UMETTS: A Unified Framework for Emotional Text-to-Speech Synthesis with Multimodal PromptsAlibaba · IEEE International Conference on Acoustics Speech and Signal Processing22 citationsMar 12, 2025Enhancing Low-Resource ASR through Versatile TTS: Bridging the Data GapAlibaba · IEEE International Conference on Acoustics Speech and Signal Processing22 citationsMar 12, 2025Distillation and Pruning for Scalable Self-Supervised Representation-Based Speech Quality AssessmentMicrosoft · IEEE International Conference on Acoustics Speech and Signal Processing20 citationsMar 12, 2025Chain-of-Thought Prompting for Speech TranslationNVIDIA · IEEE International Conference on Acoustics Speech and Signal Processing20 citationsMar 12, 2025Revise, Reason, and Recognize: LLM-Based Emotion Recognition via Emotion-Specific Prompts and ASR Error CorrectionNVIDIA · IEEE International Conference on Acoustics Speech and Signal Processing19 citationsMar 12, 2025EagerLog: Active Learning Enhanced Retrieval Augmented Generation for Log-based Anomaly DetectionAlibaba · IEEE International Conference on Acoustics Speech and Signal Processing16 citationsMar 12, 2025Generative Speech Foundation Model Pretraining for High-Quality Speech Extraction and RestorationNVIDIA · IEEE International Conference on Acoustics Speech and Signal Processing15 citationsMar 12, 2025ZipEnhancer: Dual-Path Down-Up Sampling-based Zipformer for Monaural Speech EnhancementAlibaba · IEEE International Conference on Acoustics Speech and Signal Processing15 citationsMar 12, 2025Exploring Text-Queried Sound Event Detection with Audio Source SeparationAlibaba · IEEE International Conference on Acoustics Speech and Signal Processing14 citationsMar 12, 2025A Domain Adaptation Framework for Speech Recognition Systems with Only Synthetic dataMeta · IEEE International Conference on Acoustics Speech and Signal Processing14 citationsMar 12, 2025