Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Staying In Character: Perspective-Bounded Memory For Book-Based Role-Playing AgentsAlibaba · arXiv (Cornell University)Jun 24RackOps: Software Architecture and Automation Patterns for Large-Scale Server Rack ValidationMicrosoft · International Journal of Computer ApplicationsJun 24SARA: Unlocking Multilingual Knowledge in Mixture-of-Experts via Semantically Anchored Routing AlignmentAlibaba · arXiv (Cornell University)Jun 24Disease-Centric Vision-Language Pretraining with Hybrid Visual Encoding for 3D Computed TomographyAlibaba · arXiv (Cornell University)Jun 24Large Models for Time Series and Spatio-Temporal Data: A Survey and OutlookAlibaba · ACM Computing Surveys57 citationsJun 23SHERLOC: Structured Diagnostic Localization for Code Repair AgentsNVIDIA · arXiv (Cornell University)1 citationJun 23The Reinvention Grammar: How AI Is Redrawing the Edges of HCIAlphabet · interactions1 citationJun 23I4U’s Official and Streamlined Audio Systems for NIST SRE24Microsoft · The Speaker and Language Recognition Workshop (Odyssey)Jun 23Multi-expert ensemble models for cyber adversary behavior predictionDatabricks · European Conference on Modelling and Simulation (ECMS)Jun 23Certification of Machine Learning Models via Directional SharpnessAlphabet · arXiv (Cornell University)Jun 23Detecting and Controlling Sycophancy with Cascading Linear FeaturesGoogle DeepMind · arXiv (Cornell University)Jun 23Certification of Machine Learning Models via Directional SharpnessAlphabet · arXiv (Cornell University)Jun 23ActPlane: Programmable OS-Level Policy Enforcement for Agent HarnessesAlibaba · arXiv (Cornell University)Jun 23Efficient Analytic Uncertainty Quantification for Multi-Modal RegressionGoogle DeepMind · arXiv (Cornell University)Jun 23Beyond Trajectory Imitation: Strategy-Guided Policy Optimization for LLM ReasoningMeta · arXiv (Cornell University)Jun 23AsyncOPD: How Stale Can On-Policy Distillation Be?Microsoft · arXiv (Cornell University)Jun 23Beyond Monotonic Progress: Retry-Supervised Value Learning for Robot ImitationMicrosoft · arXiv (Cornell University)Jun 23OpenThoughts-Agent: Data Recipes for Agentic ModelsMicrosoft · arXiv (Cornell University)Jun 23Cross-Lingual Exploration for Parametric KnowledgeAlphabet · arXiv (Cornell University)Jun 23CALIBER: Calibrating Confidence Before and After Reasoning in Language ModelsCohere · arXiv (Cornell University)Jun 23Dialogue to Discovery: Attribute-Aware Preference Elicitation for Conversational Product Search AssistantsMicrosoft · arXiv (Cornell University)Jun 23Practical Occluder Generation for Mobile GamesMeta · IEEE Transactions on Visualization and Computer GraphicsJun 23A Human-Centric Framework for Data Attribution in Large Language ModelsAllen Institute for AI · ACM Conference on Fairness, Accountability, and Transparency (FAccT)Jun 23Can Large Language Models Really Recognize Your Name?Alphabet · ACM Conference on Fairness, Accountability, and Transparency (FAccT)Jun 23BPFComposer: Towards deterministic and safe composition of eBPF Programs (and their Shared state)Meta · ACM International Conference on Distributed and Event-Based Systems (DEBS)1 citationJun 22