Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
COMPASS: The 2nd International Workshop on Socio-technical Approaches to Content Moderation and Platform GovernanceOpenAI · ACM Conference on Computer Supported Cooperative Work (CSCW)Oct 9TransAct V2: Production System for Lifelong User Sequence Modeling at ScaleOpenAI · ACM Conference on Recommender Systems (RecSys)Sep 25Multi-Probe Zero Collision Hash (MPZCH): Mitigating Embedding Collisions and Enhancing Model Freshness in Large-Scale RecommendersMeta, OpenAI · ACM Conference on Recommender Systems (RecSys)Sep 25ParA-LLM: A Unified Approach to Paralinguistic and Acoustic Speech UnderstandingOpenAI · arXiv (Cornell University)Sep 19Inoculation Midtraining with Learned NeologismsOpenAI · arXiv (Cornell University)Sep 14Kunlun: Establishing Scaling Laws for Massive-Scale Recommendation Systems through Unified Architecture DesignMeta, OpenAI · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)Aug 7Learning to Coordinate Symbolic Tools: LLM Agents for Verified Sum-of-Squares CertificatesOpenAI · arXiv (Cornell University)Jul 31Capacity Analysis of Vector Symbolic ArchitecturesOpenAI · Journal of Artificial Intelligence Research6 citationsJul 25Role Steering of Language Models for Social SimulationsGoogle DeepMind, OpenAI · arXiv (Cornell University)Jul 9Reference-Based Distillation Detection in LLMsOpenAI · arXiv (Cornell University)Jun 19The Multipath Reliable Connection (MRC) TransportMicrosoft, NVIDIA, OpenAI · arXiv (Cornell University)Jun 16ExpRL: Exploratory RL for LLM Mid-TrainingOpenAI · arXiv (Cornell University)Jun 15Findings of the MAGMaR 2026 Shared TaskOpenAI · arXiv (Cornell University)Jun 10Findings of the MAGMaR 2026 Shared TaskOpenAI · arXiv (Cornell University)Jun 10Large-Scale Regularized Matching on GPU ClustersOpenAI · arXiv (Cornell University)Jun 5LLM and Agents for Recommendation Systems (LARS)Meta, OpenAI · International World Wide Web Conference (WWW)May 28DraftNEPABench: A Benchmark for Drafting NEPA Document Sections with Coding AgentsOpenAI · ACM Conference on AI and Agentic Systems (CAIS)May 22ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?Alphabet, Anthropic, OpenAI · arXiv (Cornell University)3 citationsMay 11One Turn Too Late: Learning When to Intervene Against Multi-Turn Malicious IntentOpenAI · arXiv (Cornell University)May 7Evaluating large language models for accuracy incentivizes hallucinationsOpenAI · Nature23 citationsApr 22HorizonBench: Long-Horizon Personalization with Evolving PreferencesOpenAI · arXiv (Cornell University)Apr 19HALO: Hardware-Aware Quantization with Low Critical-Path-Delay Weights for LLM AccelerationOpenAI · Proceedings of the AAAI Conference on Artificial Intelligence1 citationMar 14Triton-Sanitizer: A Fast and Device-Agnostic Memory Sanitizer for Triton with Rich Diagnostic ContextAlphabet, Anthropic, Meta, OpenAI · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)1 citationMar 10PASTA: A Modular Program Analysis Tool Framework for AcceleratorsOpenAI · arXiv (Cornell University)Feb 25PASTA: A Modular Program Analysis Tool Framework for AcceleratorsOpenAI · arXiv (Cornell University)Feb 25