Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
BidirLM: From Text to Omnimodal Bidirectional Encoders by Adapting and Composing Causal LLMsCohere · arXiv (Cornell University)Apr 2Spatial Reasoning is Not a Free Lunch: A Controlled Study on LLaVACohere · arXiv (Cornell University)Mar 13Tiny Aya: Bridging Scale and Multilingual DepthCohere · arXiv (Cornell University)Mar 12LLM2Vec-Gen: Generative Embeddings from Large Language ModelsCohere · arXiv (Cornell University)Mar 11ITLC at SemEval-2026 Task 11: Normalization and Deterministic Parsing for Formal Reasoning in LLMsCohere · arXiv (Cornell University)Mar 3When AI Benchmarks Plateau: A Systematic Study of Benchmark SaturationCohere · arXiv (Cornell University)2 citationsFeb 18A Unified Framework for Rethinking Policy Divergence Measures in GRPOCohere · arXiv (Cornell University)Feb 5A benchmark of expert-level academic questions to assess AI capabilitiesAlphabet, Anthropic, Cohere, Google DeepMind, Microsoft, OpenAI · Nature61 citationsJan 28The Spatial Blindspot of Vision-Language ModelsCohere · arXiv (Cornell University)Jan 15Lost in Simulation: LLM-Simulated Users are Unreliable Proxies for Human Users in Agentic EvaluationsCohere · Annual Meeting of the Association for Computational Linguistics (ACL)1 citationJan 1ITLC at SemEval-2026 Task 11: Normalization and Deterministic Parsing for Formal Reasoning in LLMsCohere · International Workshop on Semantic Evaluation (SemEval)Jan 1Improving the OOD Performance of Closed-Source LLMs on NLI Through Strategic Data SelectionCohere · Findings of the Association for Computational Linguistics: EACLJan 1MAPS: A Multilingual Benchmark for Agent Performance and SecurityCohere · Findings of the Association for Computational Linguistics: EACLJan 1AMIYA Shared Task: Arabic Modeling In Your Accent at VarDial 2026Cohere · Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial)Jan 1MIMIC: Integrating Diverse Personality Traits for Better Game Testing Using Large Language ModelCohere · IEEE/ACM International Conference on Automated Software Engineering (ASE)Nov 16, 2025The Art of Asking: Multilingual Prompt Optimization for Synthetic DataCohere · arXiv (Cornell University)Oct 22, 2025Knowledge Explorer: An Agentic AI Framework for Interactive, Personalized and Multilingual Learning ExperienceCohere · ACM Conference on Computer Supported Cooperative Work (CSCW)Oct 17, 2025Making, not Taking, the Best of NCohere · arXiv (Cornell University)Oct 1, 2025Preliminary Ranking of WMT25 General Machine Translation SystemsAlphabet, Cohere, Microsoft · HALAug 11, 2025Large Language Models: Architecture and Training. From Next-Word Prediction to ReasoningCohere · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)Aug 3, 2025Exploring The Effectiveness of In-Context Methods in Human-Aligned Large Language Models Across LanguagesCohere · JUTI Jurnal Ilmiah Teknologi InformasiJul 8, 2025Understanding and Mitigating Toxicity in Image-Text Pretraining Datasets: A Case Study on LLaVACohere · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)Jun 11, 2025MAPS: A Multilingual Benchmark for Agent Performance and SecurityCohere · arXiv (Cornell University)May 21, 2025Aya Vision: Advancing the Frontier of Multilingual MultimodalityCohere · arXiv (Cornell University)1 citationMay 13, 2025Crosslingual Reasoning through Test-Time ScalingCohere · arXiv (Cornell University)May 8, 2025