Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Half-S: Halving the Scale for Near-Lossless 4-Bit LLM TrainingSenseTime · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1Mind Reader: Latent User Demand-Guided Content Optimization for Generative Search EngineSenseTime · Annual Meeting of the Association for Computational Linguistics (ACL)Jan 1Towards Robust Real-World Spreadsheet Understanding with Multi-Agent Multi-Format ReasoningSenseTime · Annual Meeting of the Association for Computational Linguistics (ACL)Jan 1ReinDriveGen: Reinforcement Post-training for Out-of-Distribution Driving Scene GenerationSenseTime · Lecture notes in computer scienceJan 1Demystifying Video ReasoningSenseTime · Lecture notes in computer scienceJan 1Heterogeneous Federated Dynamic Graph HyperNetwork for Image ClassificationSenseTime · IEEE Transactions on Image ProcessingJan 1The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified AutoencodingSenseTime · Lecture notes in computer scienceJan 1Pistachio: Towards Synthetic, Balanced, and Long-Form Video Anomaly BenchmarksSenseTime · Lecture notes in computer scienceJan 1HistoryNetv2: Structure-Aware Colorization of Historical Garment ImagesSenseTime · International Conference on Virtual Reality and VisualizationDec 19, 2025Depth-Aligned Uniform Foreground BEV Feature for Multimodal 3D Object DetectionSenseTime · International Conference on Virtual Reality and VisualizationDec 19, 2025Align then clip: Refining graph for face clusteringSenseTime · Neural NetworksDec 13, 2025Towards Fine-Grained Recognition with Large Visual Language Models: Benchmark and Optimization StrategiesSenseTime · arXiv (Cornell University)Dec 11, 2025HTMMM: Novel Hybrid Truncated Montgomery Modular Multiplication Algorithm and Hardware ArchitectureSenseTime · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems1 citationDec 8, 2025TVR-Ranking: A Dataset for Ranked Video Moment Retrieval with Imprecise QueriesSenseTime · Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region (SIGIR-AP)1 citationDec 3, 2025A Flexible and Scalable Framework for Video Moment SearchSenseTime · Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region (SIGIR-AP)1 citationDec 3, 2025Artemis: Structured Visual Reasoning for Perception Policy LearningSenseTime · arXiv (Cornell University)Dec 1, 2025TRivia: Self-supervised Fine-tuning of Vision-Language Models for Table RecognitionSenseTime · arXiv (Cornell University)Dec 1, 2025PathOrchestra: a comprehensive foundation model for computational pathology with over 100 diverse clinical-grade tasksSenseTime · npj Digital Medicine22 citationsNov 19, 2025Scaling Spatial Intelligence with Multimodal Foundation ModelsSenseTime · arXiv (Cornell University)Nov 17, 2025Towards Efficient LLM Inference via Collective and Adaptive Speculative DecodingSenseTime · International Conference for High Performance Computing, Networking, Storage and Analysis (SC)2 citationsNov 12, 2025TokenSim: Enabling Hardware and Software Exploration for Large Language Model Inference SystemsAlibaba, SenseTime · Lecture notes in computer science1 citationNov 3, 2025Data-Free Cloud-Edge Distillation for Safe and Efficient Intelligent CommunicationsSenseTime · IEEE Journal on Selected Areas in CommunicationsNov 3, 2025A renaissance of explicit motion information mining from transformers for action recognitionSenseTime · Pattern Recognition1 citationOct 31, 2025Graph Unlearning Meets Influence-aware Negative Preference OptimizationSenseTime · ACM International Conference on Multimedia (ACM MM)1 citationOct 25, 2025Identify, Isolate, and Purge: Mitigating Hallucinations in LVLMs via Self-Evolving DistillationSenseTime · ACM International Conference on Multimedia (ACM MM)Oct 25, 2025