Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
SparkShield at ArA-DF 2026: Robust Arabic Speech Deepfake Detection via Realistic Audio Augmentation and Multi-Scale XLS-R Score FusioniFlytek · Arabic Natural Language Processing Workshop (WANLP)Jan 1COIN: A Live, Large-scale Benchmark for Semantics-to-Input Code ReasoningMicrosoft · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1ACTOR: Agentic CT Reasoning with Radiologist-Aligned ActionsAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1PEARL: Perturbation Efficient Alignment Group Relative Reinforcement LearningMicrosoft · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1LUPE: Long-History User Profile Evolution for LLM-based RecommendationMicrosoft · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1Avoidance Learning of Failure Modes Produces Robust Tool PlannersNVIDIA · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1Mosaic: Automated Intent Description Generation for Multi-Label ClassificationMicrosoft · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1Detecting Post-generation Edits to Watermarked LLM Outputs via Error-Correcting CodesAlphabet · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1Optimal Partition Selection with Rényi Differential PrivacyAlphabet · arXiv (Cornell University)Jan 1Auto-Range Adaptation Based Mixed-Signal Circuit for Lossy Capacitive SensorsAlphabet · IEEE Transactions on Instrumentation and MeasurementJan 1Building Auditable AI Text Detectors with Sparse AutoencodersGoogle DeepMind · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1After the Attacker Leaves: Benchmarking Carryover Attacks on LLM AgentsSenseTime · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1Diagnostic Analysis for Large Language Model ReasoningMeta · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1DeepSEA: A Multilingual Evaluation Benchmark for Southeast AsiaAlphabet · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1Revocable Identity-Based Authenticated Key Exchange: Generic and Direct ConstructionsTechnology Innovation Institute · IEICE Transactions on Fundamentals of Electronics Communications and Computer SciencesJan 1Automated Hardware Synthesis at Scale: A View From The TrenchesAlphabet · IEEE MicroJan 1MAAC: M ulti- A ccelerator A rchitecture and C ommunication Co-design for Accelerating Graph Neural Networksd-Matrix · IEEE Transactions on ComputersJan 1Med-MARS: Modifier-Aware Referring Segmentation for Medical ImagesAlibaba · IEEE Transactions on Medical ImagingJan 1Dual-Branch Learned Image Compression with Conditional Entropy Modeling and Deformable Convolution-based AttentionAlphabet · IEEE Transactions on Circuits and Systems for Video TechnologyJan 1Thirty Years of Online Video: How the Postage-Stamp Sized Video Grew UpAlphabet · IEEE Internet ComputingJan 1Patch Collaboration with Contrastive Learning for Weakly Supervised Semantic SegmentationMicrosoft · Computers, materials & continua/Computers, materials & continua (Print)Jan 1UniData: Universal Multimodal Instruction Generation PipelineAlibaba · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1V-CoLA: Vision Token Compression with Linear AttentionAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1Routing-Embedded Locking: Distributed Coordination Without a Lock ServiceMicrosoft · IEEE Internet ComputingJan 1Edge–Cloud Digital Service Loop Framework for Real-Time Cardiac Patient Monitoring and Predictive Intervention in IoT-Enabled Healthcare SystemsMicrosoft · IEEE Internet of Things MagazineJan 1