Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Causal Prompts for Open-Vocabulary Video Instance SegmentationSenseTime · IEEE Transactions on Pattern Analysis and Machine Intelligence1 citationMar 3Narrative Scaffolding: A Narrative-First Framework for Data-Driven SensemakingAllen Institute for AI · ACM International Conference on Intelligent User Interfaces (IUI)1 citationMar 3RewriteGen: Autonomous Query Optimization for Retrieval-Augmented Large Language Models via Reinforcement LearningiFlytek · Electronics1 citationMar 3Gazeify Then Voiceify: Physical Object Referencing Through Gaze and Voice Interaction with Displayless Smart GlassesMeta · ACM International Conference on Intelligent User Interfaces (IUI)1 citationMar 3ReUseIt: Synthesizing Reusable AI Agent Workflows for Web AutomationMicrosoft · ACM International Conference on Intelligent User Interfaces (IUI)1 citationMar 3Expected Reward Prediction, with Applications to Model RoutingGoogle DeepMind · arXiv (Cornell University)Mar 3Trade-offs in Ensembling, Merging and Routing Among Parameter-Efficient ExpertsMicrosoft · arXiv (Cornell University)Mar 3Sharing is caring: Attestable and Trusted Workflows out of Distrustful ComponentsMicrosoft · arXiv (Cornell University)Mar 3Quantum Lego Power-up: Designing Transversal Gates with Tensor NetworksMicrosoft · arXiv (Cornell University)Mar 3Contextualized Privacy Defense for LLM AgentsMicrosoft · arXiv (Cornell University)Mar 3S2CDR: Smoothing-Sharpening Process Model for Cross-Domain RecommendationAlibaba · arXiv (Cornell University)Mar 3Through the Lens of Contrast: Self-Improving Visual Reasoning in VLMsAlibaba · arXiv (Cornell University)Mar 3Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool UseMicrosoft · arXiv (Cornell University)Mar 3Extending the Formalism and Theoretical Foundations of Cryptography to AIMicrosoft · arXiv (Cornell University)Mar 3How Controllable Are Large Language Models? A Unified Evaluation across Behavioral GranularitiesAlibaba · arXiv (Cornell University)Mar 3ITLC at SemEval-2026 Task 11: Normalization and Deterministic Parsing for Formal Reasoning in LLMsCohere · arXiv (Cornell University)Mar 3ParEVO: Synthesizing Code for Irregular Data: High-Performance Parallelism through Agentic EvolutionAlphabet · arXiv (Cornell University)Mar 3Improving Diffusion Planners by Self-Supervised Action Gating with EnergiesMicrosoft · arXiv (Cornell University)Mar 3"Un-default" Behavior Tuning: Specifying Model Behavior outside the Norm with LLM Self-Playing and Self-ImprovingMicrosoft · ACM International Conference on Intelligent User Interfaces (IUI)Mar 3PopSignAI: Towards Using Sign Language Recognition Games to Improve American Sign Language Learning in Novice SignersAlphabet · ACM International Conference on Intelligent User Interfaces (IUI)Mar 3A Physically Unclonable Function With Less Than 4.16E–7 BER Featuring Secure In-Cell HCI Burn-In and nMOS-Dominant PUF Data GenerationNVIDIA · IEEE Journal of Solid-State CircuitsMar 3Automatically Engineering Trusted Software: A Research RoadmapMicrosoft · ACM Transactions on Software Engineering and Methodology2 citationsMar 2CARE: Towards Clinical Accountability in Multi-Modal Medical Reasoning with an Evidence-Grounded Agentic FrameworkMicrosoft · arXiv (Cornell University)1 citationMar 2Quantum Computational Complexity of Matrix FunctionsTechnology Innovation Institute · PRX Quantum1 citationMar 2DreamReader: An Interpretability Toolkit for Text-to-Image ModelsNVIDIA · arXiv (Cornell University)Mar 2