Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Executable but Unfaithful: Mock Object, Stub, and Assertion Generation by LLMs and Coding AgentsMistral AI · arXiv (Cornell University)Oct 10Unconstrained CTI-REALM with Open-WeightsMistral AI · arXiv (Cornell University)Oct 9The Life Cycle of a Massive Activation: Stochastic Birth, Weight-Decay-Driven Growth, and Competitive ConsolidationMistral AI · arXiv (Cornell University)Sep 30Le Critique: Privileged Value Functions for LLM Reinforcement LearningMistral AI · arXiv (Cornell University)Aug 17Brief Announcement: Byzantine Machine Learning, MultiKrum and an Optimal Notion of RobustnessMistral AI · ACM Symposium on Principles of Distributed Computing (PODC)Jul 1Counsel: A Meta-Evaluation Dataset for Agentic TasksCohere, Google DeepMind, Mistral AI · arXiv (Cornell University)Jun 19Reasoning Arena: Trace Tournaments When Verifiable Rewards Fall ShortMistral AI · arXiv (Cornell University)Jun 8Collaborative LLM Agents for End-to-End Software DevelopmentMicrosoft, Mistral AI · International World Wide Web Conference (WWW)May 28Data Repetition Beats Data Scaling in Long-CoT Supervised Fine-TuningMistral AI, NVIDIA · arXiv (Cornell University)Feb 11Scale Can’t Overcome Pragmatics: The Impact of Reporting Bias on Vision-Language ReasoningAllen Institute for AI, Mistral AI · Transactions of the Association for Computational Linguistics2 citationsJan 1Spherical Leech Quantization for Visual Tokenization and GenerationMistral AI · arXiv (Cornell University)Dec 16, 2025Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition EvaluationHugging Face, Mistral AI, NVIDIA, OpenAI · arXiv (Cornell University)1 citationOct 8, 2025ShiQ: Bringing back Bellman to LLMsCohere, Mistral AI · neural information processing systemsJan 1, 2025Representation Consistency for Accurate and Coherent LLM Answer AggregationMistral AI · neural information processing systemsJan 1, 2025