Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
[MM/AI] Mental Models in Human-AI Interaction: Methods and Challenges in the Generative and Agentic AI Era (Workshop)Microsoft · arXiv (Cornell University)Sep 15High Probability Streaming Lower Bounds for $F_2$ EstimationAlphabet · arXiv (Cornell University)Sep 15PCap: Personalized Retrieval-Stage Diversity Capping in Facebook MarketplaceMeta · arXiv (Cornell University)Sep 15You Shall Not Pass into Ring-0! A User Privacy-Friendly Anti-Cheat Architecture for Personal ComputersMicrosoft · arXiv (Cornell University)Sep 15RadarMind: cognitive AI with mmWave sensing for human-aware intelligent automationAlphabet, Microsoft · Journal on Advances in Signal ProcessingSep 15AgentPProf: Semantic Profiler for Long Horizon AI AgentsAlibaba · arXiv (Cornell University)Sep 14Regularized Emphatic Temporal-Difference Learning: Stability under Constant StepsizesMicrosoft · arXiv (Cornell University)Sep 14Register Tokens for Bounded-State Reasoning in Diffusion Language ModelsMicrosoft · arXiv (Cornell University)Sep 14Towards Scalable Measurement of Durable SkillsAlphabet · arXiv (Cornell University)Sep 14Randomized query complexity can beat certificate complexityAlphabet · arXiv (Cornell University)Sep 14Dream-RSI: Recursive Self-Improvement through Evolving WorldsGoogle DeepMind · arXiv (Cornell University)Sep 14Inoculation Midtraining with Learned NeologismsOpenAI · arXiv (Cornell University)Sep 14Not All Prompts Are Equal: Exploration-Guided Prompt Scaffolding for Multimodal Reinforcement Post-TrainingAlibaba · arXiv (Cornell University)Sep 14Learning to Coach for Experiential LearningMicrosoft · arXiv (Cornell University)Sep 14PACE: Progressive Angular-to-Norm Contrastive EmbeddingAlibaba · arXiv (Cornell University)Sep 14Fermionic quantum error correction is never freeTechnology Innovation Institute · arXiv (Cornell University)Sep 14Self-Evolving Memory for Generative RecommendationMeta · arXiv (Cornell University)Sep 14LazFormer: Scaling Transformers for Industrial Recommendation via Transferable Generative Pre-trainingAlibaba · arXiv (Cornell University)Sep 14MTAC-IFBench: Benchmarking Instruction-Following in Multi-Turn Agentic CodingZhipu AI · arXiv (Cornell University)Sep 14V-ICAL Bench: Evaluating Video In-Context Learning for Multimodal Agents in Interactive EnvironmentsMicrosoft · arXiv (Cornell University)Sep 14The Imitation Game: When LLMs Learn to Reason Like Programs via Code-Centric Reasoning Data SynthesisAlibaba · arXiv (Cornell University)Sep 13Lightning Weave: Improving the Accuracy-Efficiency Frontier of Reasoning Models through Capability CompositionNVIDIA · arXiv (Cornell University)Sep 13Sharing standardized image-derived data in computational pathology using DICOMAlphabet · arXiv (Cornell University)Sep 13VARG: Value-Aware and Ranking-Aligned Generative Retrieval for Dynamic E-commerce SearchAlibaba · arXiv (Cornell University)Sep 13CompCQR: Compositional Query Generation for Training-Free Conversational SearchLG AI Research · arXiv (Cornell University)Sep 13