Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
PointHPS: Cascaded 3D Human Pose and Shape Estimation from Point CloudsSenseTime · International Journal of Computer Vision3 citationsApr 7EVA: Efficient Reinforcement Learning for End-to-End Video AgentSenseTime · arXiv (Cornell University)Mar 24ACPO: Counteracting Likelihood Displacement in Vision-Language Alignment with Asymmetric ConstraintsSenseTime · arXiv (Cornell University)Mar 23FailureMem: A Failure-Aware Multimodal Framework for Autonomous Software RepairSenseTime · arXiv (Cornell University)Mar 18CLIPDet3D: Vision-Language Collaborative Distillation for 3D Object DetectionSenseTime · Proceedings of the AAAI Conference on Artificial Intelligence1 citationMar 14MathSmith: Towards Extremely Hard Mathematical Reasoning by Forging Synthetic Problems with a Reinforced PolicySenseTime · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14Injection Without Distortion: Geometrically Constrained Knowledge Enhancement for Vision-Language ModelsSenseTime · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14RAA: Achieving Interactive Remove/Add Anything via Fully Synthetic DataSenseTime · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14LLMC+: Benchmarking Vision-Language Model Compression with a plug-and-play ToolkitSenseTime · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14Modality and Task Adaptation for Enhanced Zero-shot Composed Image RetrievalSenseTime · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14SARA: Controllable makeup transfer with semantic-guided alignment and region-adaptive normalizationSenseTime · Computer Vision and Image Understanding3 citationsMar 9Causal Prompts for Open-Vocabulary Video Instance SegmentationSenseTime · IEEE Transactions on Pattern Analysis and Machine IntelligenceMar 3CURE: A Multimodal Benchmark for Clinical Understanding and Retrieval EvaluationSenseTime · arXiv (Cornell University)Feb 28AIDABench: AI Data Analytics BenchmarkSenseTime · arXiv (Cornell University)Feb 27ICA: Information-Aware Credit Assignment for Visually Grounded Long-Horizon Information-Seeking AgentsSenseTime · arXiv (Cornell University)Feb 11SCALAR: Spatial-concept alignment for robust vision in harsh open worldSenseTime · Pattern Recognition2 citationsFeb 3Focus-dLLM: Accelerating Long-Context Diffusion LLM Inference via Confidence-Guided Context FocusingSenseTime · arXiv (Cornell University)Feb 2Focus-dLLM: Accelerating Long-Context Diffusion LLM Inference via Confidence-Guided Context FocusingSenseTime · arXiv (Cornell University)Feb 2Towards universal X-ray security inspection: a benchmark and stereoscopic-aware oriented prohibited item detection frameworkiFlytek, SenseTime · Science China Information Sciences1 citationJan 29Practical Continual Forgetting for Pre-Trained Vision ModelsSenseTime · IEEE Transactions on Pattern Analysis and Machine Intelligence3 citationsJan 15CAS-ViT: Convolutional Additive Self-Attention Vision Transformers for Efficient Mobile ApplicationsSenseTime · IEEE Transactions on Image Processing52 citationsJan 1PET-SQL: A Prompt-Enhanced Two-Round Refinement of Text-to-SQL with Cross-ConsistencySenseTime · Lecture notes in computer science10 citationsJan 1Integrating Large Language Models Into Recommendation via Mutual Augmentation and Adaptive AggregationSenseTime · IEEE Journal of Selected Topics in Signal Processing7 citationsJan 1An End-to-End Optimized Lensless System for Privacy-Preserving Face VerificationNVIDIA, SenseTime · IEEE Transactions on Image Processing1 citationJan 1Focus-dLLM: Accelerating Long-Context Diffusion LLM Inference via Confidence-Guided Context FocusingSenseTime · Annual Meeting of the Association for Computational Linguistics (ACL)Jan 1