Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
TabReliBench: Evaluating Tabular Foundation Models Beyond Predictive AccuracyCerebras Systems · arXiv (Cornell University)Oct 9Performance-portable GPU acceleration of the hybrid particle-in-cell code dHybridRCerebras Systems · arXiv (Cornell University)Sep 23Self-drafting with Uno on a mixture of experts: serving and training an adapter for Gemma 4 26B A4BCerebras Systems · arXiv (Cornell University)Sep 3MemoryLACE: Memory Lifecycle-Aware Consolidation and Evidence RetrievalCerebras Systems · arXiv (Cornell University)Sep 2Gated Recurrent Transformers: Expressive Depth through Recurrent ModulationCerebras Systems · arXiv (Cornell University)Aug 15DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal GenerationCerebras Systems · arXiv (Cornell University)May 30DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal GenerationCerebras Systems · arXiv (Cornell University)May 30CodeQuant: Unified Clustering and Quantization for Enhanced Outlier Smoothing in Low-Precision Mixture-of-ExpertsCerebras Systems · arXiv (Cornell University)Apr 12Beyond Exascale: Dataflow Domain Translation on a Cerebras ClusterCerebras Systems · arXivJan 9DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal GenerationCerebras Systems · Annual Meeting of the Association for Computational Linguistics (ACL)Jan 1Nanda Family: Open-Weights Generative Large Language Models for HindiCerebras Systems · Conference of the European Chapter of the Association for Computational LinguisticsJan 1Systematic Exploration of Small-Molecule Binding via a Large Language Model Trained on Textualized Protein–Ligand InteractionsCerebras Systems · Molecules1 citationNov 22, 2025Batch Tiling on Attention: Efficient Mixture of Experts Training on Wafer-Scale ProcessorsCerebras Systems · International Conference for High Performance Computing, Networking, Storage and Analysis (SC)1 citationNov 7, 2025Demystifying Synthetic Data in LLM Pre-training: A Systematic Study of Scaling Laws, Benefits, and PitfallsCerebras Systems · arXiv (Cornell University)Oct 2, 2025A distributed inference algorithm for Dirichlet process mixture models with exponential family componentsCerebras Systems · NeurocomputingAug 6, 2025EDAN: Towards Understanding Memory Parallelism and Latency Sensitivity in HPCCerebras Systems · ACM International Conference on Supercomputing (ICS)1 citationJun 8, 2025Wafer-Scale Integration for AI – The Holy Grail?Cerebras Systems · IEEE Symposium on VLSI Technology and Circuits (VLSI Technology and Circuits)Jun 8, 2025Llama-3-Nanda-10B-Chat: An Open Generative Large Language Model for HindiCerebras Systems · arXiv (Cornell University)Apr 8, 2025Slide FFT on a homogeneous mesh in wafer-scale computingCerebras Systems · Discover Computing1 citationMar 12, 2025Breaking the mold: Overcoming the time constraints of molecular dynamics on general-purpose hardwareCerebras Systems · The Journal of Chemical Physics8 citationsFeb 19, 2025Instruction Tuning on Public Government and Cultural Data for Low-Resource Language: a Case Study in KazakhCerebras Systems · arXiv (Cornell University)Feb 19, 2025Preparing MPICH for exascaleCerebras Systems, Meta, Microsoft, NVIDIA · The International Journal of High Performance Computing Applications8 citationsJan 9, 2025Instruction Tuning on Public Government and Cultural Data for Low-Resource Language: a Case Study in KazakhCerebras Systems · Annual Meeting of the Association for Computational Linguistics (ACL)2 citationsJan 1, 2025DREAM: Drafting with Refined Target Features and Entropy-Adaptive Cross-Attention Fusion for Multimodal Speculative DecodingCerebras Systems · neural information processing systems1 citationJan 1, 2025Don't be lazy: CompleteP enables compute-efficient deep transformersCerebras Systems · neural information processing systems1 citationJan 1, 2025