Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Grad-ECLIP: Gradient-Based Visual and Textual Explanations for CLIPSenseTime · IEEE Transactions on Pattern Analysis and Machine Intelligence2 citationsJul 17Breaking the Quality--Intelligibility Trade-off in Streaming Target Speaker Extraction via Deep-Feature-Anchored Preference OptimizationSenseTime · arXiv (Cornell University)Jul 11Enjoy Your Talk: A Human-Centered Benchmark for Multi-Turn Dialogue with Decoupled User Simulation, Target Modeling, and JudgingSenseTime · arXiv (Cornell University)Jul 11DeVAR: Low-Dose CT Denoising via Visual Autoregressive ModelingSenseTime · arXiv (Cornell University)Jun 26SUDA: Simultaneous unsupervised knowledge distillation and adaptation of foundation models for efficient pathological image analysisSenseTime · Medical Image AnalysisJun 26Revisiting InternVL: A Systematic Technical Framework for Building Powerful Open-Source Vision-Language ModelsSenseTime · IEEE Transactions on Pattern Analysis and Machine IntelligenceJun 10Prisma-World: Camera-Controllable Multi-Agent Video World ModelSenseTime · arXiv (Cornell University)Jun 8Wavelet spectral-aware Kolmogorov-Arnold Network for organ and tumor segmentationSenseTime · Computerized Medical Imaging and Graphics1 citationJun 5Toward Immersive Volumetric Space: Capture, Reconstruction, and ApplicationSenseTime · IEEE Transactions on Circuits and Systems for Video TechnologyJun 5From Pixels to Words -- Towards Native One-Vision Models at ScaleSenseTime · arXiv (Cornell University)May 27InterSketch: An Interleaved Reasoning Model with Self-correcting Visual Sketch and Stepwise RewardSenseTime · arXiv (Cornell University)May 26DisagFusion: Asynchronous Pipeline Parallelism and Elastic Scheduling for Disaggregated Diffusion ServingSenseTime · arXiv (Cornell University)May 25USV: Towards Understanding the User-generated Short-form VideosSenseTime · arXiv (Cornell University)May 20SemaVoice: Semantic-Aware Continuous Autoregressive Speech SynthesisSenseTime · arXiv (Cornell University)May 16How Should LLMs Listen While Speaking? A Study of User-Stream Routing in Full-Duplex Spoken DialogueSenseTime · arXiv (Cornell University)May 11V-ABS: Action-Observer Driven Beam Search for Dynamic Visual ReasoningSenseTime · arXiv (Cornell University)May 11DASR+: Training Domain Distance Aware Network for Unsupervised Image Super-ResolutionSenseTime · International Journal of Computer VisionMay 7PiLLM: Resource-Efficient LLM Inference Using Workload PredictionSenseTime · European Conference on Computer SystemsApr 24PG-SE: Predictive Acceleration and Correction for Generative Speech EnhancementSenseTime · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21P2CL: Prototype-Constrained Consistent Learning — Toward Controllable and Consistent TransferSenseTime · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Performance-Guided Reinforced Active Learning for Object DetectionSenseTime · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Intrinsic Semantic Consistency Enhancement for Robust Hierarchical Understanding in VLMsSenseTime · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21OpenMobile: Building Open Mobile Agents with Task and Trajectory SynthesisSenseTime · arXiv (Cornell University)Apr 16Towards Robust Real-World Spreadsheet Understanding with Multi-Agent Multi-Format ReasoningSenseTime · arXiv (Cornell University)Apr 14Towards Robust Real-World Spreadsheet Understanding with Multi-Agent Multi-Format ReasoningSenseTime · arXiv (Cornell University)Apr 14