Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
GMM-Based Bootstrap Prototype-Aware Learning For Weakly Supervised Semantic SegmentationSenseTime · IEEE International Conference on Acoustics Speech and Signal ProcessingMar 12, 2025Efficient Long-Form Speech Recognition for General Speech In-Context LearningMicrosoft · IEEE International Conference on Acoustics Speech and Signal ProcessingMar 12, 2025Adversarial Speech-Text Pre-Training for Speech TranslationiFlytek · IEEE International Conference on Acoustics Speech and Signal ProcessingMar 12, 2025TransVDM: Motion-Constrained Video Diffusion Model for Transparent Video SynthesisAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingMar 12, 2025Semi-Supervised Multilingual Alignment with Lexical Memory for Massively Parallel Text MiningiFlytek · IEEE International Conference on Acoustics Speech and Signal ProcessingMar 12, 2025FR 2 ViT: Finetuning-free Token Reduction for Dense Prediction Through a Refinement-Reactivation ArchitectureAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingMar 12, 2025Layer-Animate for Transparent Video GenerationAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingMar 12, 2025Enhancing Video-Text Matching via Sparse Stratified SamplingAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingMar 12, 2025BEVHeight++: Toward Robust Visual Centric 3D Object DetectionAlibaba · IEEE Transactions on Pattern Analysis and Machine Intelligence74 citationsMar 11, 2025A Theory of Learning with Autoregressive Chain of ThoughtMicrosoft · arXiv (Cornell University)23 citationsMar 11, 2025Quantum simulation of boson-related Hamiltonians: techniques, effective Hamiltonian construction, and error analysisMicrosoft · Quantum Science and Technology22 citationsMar 11, 2025Training Plug-n-Play Knowledge Modules with Deep Context DistillationMicrosoft · arXiv (Cornell University)20 citationsMar 11, 2025Exploring Bias in over 100 Text-to-Image Generative ModelsAlphabet · arXiv (Cornell University)11 citationsMar 11, 2025A Performance Portable, Fully Implicit Landau Collision Operator with Batched Linear SolversNVIDIA · SIAM Journal on Scientific Computing9 citationsMar 11, 2025Seeing Beyond Haze: Generative Nighttime Image DehazingMicrosoft · arXiv (Cornell University)6 citationsMar 11, 2025The Impact of Avatar Retargeting on Pointing and Conversational CommunicationMeta · IEEE Transactions on Visualization and Computer Graphics5 citationsMar 11, 2025Leveraging Risk Models to Improve Productivity for Effective Code Un-Freeze at ScaleMeta · ACM Transactions on Software Engineering and Methodology4 citationsMar 11, 2025ESPnet-SDS: Unified Toolkit and Demo for Spoken Dialogue SystemsHugging Face · arXiv (Cornell University)2 citationsMar 11, 2025Admissible parameters for the Crossbred algorithm and semi-regular sequences over finite fieldsTechnology Innovation Institute · Designs Codes and Cryptography2 citationsMar 11, 2025Stick to Facts: Towards Fidelity-oriented Product Description GenerationAlibaba · arXiv (Cornell University)Mar 11, 2025RefactorBench: Evaluating Stateful Reasoning in Language Agents Through CodeMicrosoft · arXiv (Cornell University)19 citationsMar 10, 2025Design and analysis of binaural signal matching with arbitrary microphone arrays and listener head rotationsMeta · EURASIP Journal on Audio Speech and Music Processing10 citationsMar 10, 2025GO-NeRF: Generating Objects in Neural Radiance Fields for Virtual Reality Content CreationAlphabet · IEEE Transactions on Visualization and Computer Graphics8 citationsMar 10, 2025Hierarchical Balance Packing: Towards Efficient Supervised Fine-tuning for Long-Context LLMSenseTime · arXiv (Cornell University)3 citationsMar 10, 2025UC-MOA: Utility-Conditioned Multi-Objective Alignment for Distributional Pareto-OptimalityMicrosoft · arXiv (Cornell University)1 citationMar 10, 2025