Hybrid Transformer–Mamba language models (Jamba)
A better long-tail AI21 page because it makes the data side of Jamba visible, instead of leaving the impression that hybrid-model progress came only from architecture and not from the people shaping the data pipeline underneath it.
Memory-efficient distributed training (ZeRO)
Co-authored ZeRO: foundational memory optimizations for training very large models.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Frontier model development (GPT-4)
Co-authored the GPT-4 Technical Report: a key reference for the GPT-4-era frontier.
Open-weight frontier models (Llama 3)
Co-authored “The Llama 3 Herd of Models”.
Co-authored the GPT-4 Technical Report: a key reference for the GPT-4-era frontier.
Open code LLMs (StarCoder)
Co-authored StarCoder: a foundational open code model effort (BigCode).
Pathways-scale language modeling (PaLM)
Co-authored PaLM: Scaling Language Modeling with Pathways.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Model-written evaluations for LM behavior
Co-authored model-written evals: a practical technique for discovering and measuring LM behaviors.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Open-weight frontier models (Llama 3)
Co-authored “The Llama 3 Herd of Models”.
Open language models from Google (Gemma)
Co-authored Gemma: open models based on Gemini research and technology.
Open code LLMs (StarCoder)
Co-authored StarCoder: a foundational open code model effort (BigCode).
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Open-weight frontier models (Llama 3)
Co-authored “The Llama 3 Herd of Models”.
Small, capable models (Phi-3)
Co-authored the Phi-3 Technical Report (capable models designed for smaller footprints).
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Holistic evaluation of language models (HELM)
Co-authored HELM: a framework for evaluating language models across many axes beyond raw accuracy.
Open multimodal models (Gemma 3)
Co-authored the Gemma 3 Technical Report.
Hybrid Transformer–Mamba language models (Jamba)
One of the clearer AI21 engineering pages because it points to the people who sat between model research and training execution, not just the public-facing authorship layer.
Open-weight frontier models (Llama 3)
Co-authored “The Llama 3 Herd of Models”.
Hybrid Transformer–Mamba language models (Jamba)
A strong researcher to study if you care about the semantic side of modern language systems, especially where evaluation, structured meaning representation, and tool-using LLM architectures meet.
Open-weight frontier models (Llama 3)
Co-authored “The Llama 3 Herd of Models”.
Hybrid Transformer–Mamba language models (Jamba)
Useful for understanding the AI21 line of work that tries to combine tool use, modular reasoning, and hybrid sequence architectures instead of treating LLMs as pure next-token engines.
A strong page for the go-to-market side of frontier AI because it connects AI21's model strategy to product design, enterprise positioning, and the question of how model capabilities actually turn into customer-facing systems.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Science QA evaluation (ARC)
Co-authored ARC: an influential reasoning benchmark for question answering.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Pathways-scale language modeling (PaLM)
Co-authored PaLM: Scaling Language Modeling with Pathways.
Sequence models, large-scale ML
A high-signal researcher for understanding how DeepMind approaches generality, especially in areas where reinforcement learning, multimodality, and large-scale systems meet.
Hybrid Transformer–Mamba language models (Jamba)
Another useful AI21 algorithms page because it highlights the contributors shaping how the models behave internally, not just the infrastructure or product layer around them.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Open language models from Google (Gemma)
Co-authored Gemma: open models based on Gemini research and technology.
Open language models from Google (Gemma)
Co-authored Gemma: open models based on Gemini research and technology.
Open multimodal models (Gemma 3)
Co-authored the Gemma 3 Technical Report.
Truthfulness and hallucination evaluation
Co-authored TruthfulQA: an influential benchmark for truthfulness and falsehood mimicry in LMs.
Open, fully-documented language models (OLMo)
Co-authored OLMo: Accelerating the Science of Language Models.
Open-weight frontier models (Llama 3)
Co-authored “The Llama 3 Herd of Models”.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Open language models from Google (Gemma)
Co-authored Gemma: open models based on Gemini research and technology.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Instruction following, alignment
A useful person to study for the policy-and-deployment side of frontier AI, especially where product releases need a more explicit hazard and misuse analysis.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Open language models (Gemma 2)
Co-authored Gemma 2: improving open language models at a practical size.
Open-model frontier reports (DeepSeek-V3)
Co-authored the DeepSeek-V3 Technical Report.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Pathways-scale language modeling (PaLM)
Co-authored PaLM: Scaling Language Modeling with Pathways.
Pathways-scale language modeling (PaLM)
Co-authored PaLM: Scaling Language Modeling with Pathways.
Open-weight frontier models (Llama 3)
Co-authored “The Llama 3 Herd of Models”.
Open-weight frontier models (Llama 3)
Co-authored “The Llama 3 Herd of Models”.
Small, capable models (Phi-3)
Co-authored the Phi-3 Technical Report (capable models designed for smaller footprints).
Frontier model development (GPT-4)
Co-authored the GPT-4 Technical Report: a key reference for the GPT-4-era frontier.
Open-weight frontier models (Llama 3)
Co-authored “The Llama 3 Herd of Models”.
Latent diffusion for high-res generation
Co-authored Latent Diffusion Models: the foundation behind Stable Diffusion-style pipelines.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Model-parallel training at scale (Megatron-LM)
Co-authored Megatron-LM: a core reference for scaling transformer training via model parallelism.
Retrieval-augmented generation (RAG)
Co-authored RAG: a canonical reference for retrieval-augmented generation in NLP.
Open large-scale image-text data (LAION-5B)
Co-authored LAION-5B: a widely used open dataset for vision-language foundation models.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Open-source tooling for modern NLP (Transformers library)
Co-authored the Hugging Face Transformers paper that helped standardize modern NLP workflows.
Frontier model development (GPT-4)
Co-authored the GPT-4 Technical Report: a key reference for the GPT-4-era frontier.
Pathways-scale language modeling (PaLM)
Co-authored PaLM: Scaling Language Modeling with Pathways.
Open multimodal models (Gemma 3)
Co-authored the Gemma 3 Technical Report.
Alignment theory, reward modeling
A foundational thinker in oversight, reward modeling, and delegation-style alignment ideas that influenced much of the modern post-training conversation.
Open multimodal models (Gemma 3)
Co-authored the Gemma 3 Technical Report.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Frontier model development (GPT-4)
Co-authored the GPT-4 Technical Report: a key reference for the GPT-4-era frontier.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Open language models from Google (Gemma)
Co-authored Gemma: open models based on Gemini research and technology.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Co-authored “The Llama 3 Herd of Models”.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Few-shot vision-language models (Flamingo)
Co-authored Flamingo: an influential multimodal model for few-shot vision-language tasks.
Open code LLMs (StarCoder)
Co-authored StarCoder: a foundational open code model effort (BigCode).
Open-weight frontier models (Llama 3)
Co-authored “The Llama 3 Herd of Models”.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Open-weight frontier models (Llama 3)
Co-authored “The Llama 3 Herd of Models”.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Co-authored the Qwen2 Technical Report.
Open-model frontier reports (DeepSeek-V3)
Co-authored the DeepSeek-V3 Technical Report.
Co-authored the Qwen Technical Report.
Open-model frontier reports (DeepSeek-V3)
Co-authored the DeepSeek-V3 Technical Report.
RWKV and efficient sequence modeling
A strong RWKV page to have because he recurs across the original RWKV paper, Eagle and Finch, and Gated Slot Attention, which makes him one of the clearer repeat contributors to this whole sequence-model line rather than a one-off coauthor.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Open language models (Gemma 2)
Co-authored Gemma 2: improving open language models at a practical size.
Open-weight frontier models (Llama 3)
Co-authored “The Llama 3 Herd of Models”.
Open-weight frontier models (Llama 3)
Co-authored “The Llama 3 Herd of Models”.
Evaluation, robust NLP, systems
A key person for understanding how foundation-model evaluation, governance, and research tooling became a coherent agenda rather than a scattered set of concerns.
Open-weight frontier models (Llama 3)
Co-authored “The Llama 3 Herd of Models”.
Open, fully-documented language models (OLMo)
Co-authored OLMo: Accelerating the Science of Language Models.
Open-weight chat and foundation models (Llama 2)
Co-authored Llama 2: Open Foundation and Fine-Tuned Chat Models.
Open code models (CodeGemma)
Co-authored CodeGemma: open code models based on Gemma.
Science QA evaluation (ARC)
Co-authored ARC: an influential reasoning benchmark for question answering.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Holistic evaluation of language models (HELM)
Co-authored HELM: a framework for evaluating language models across many axes beyond raw accuracy.
Frontier model development (GPT-4)
Co-authored the GPT-4 Technical Report: a key reference for the GPT-4-era frontier.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Text-to-text transfer and pretraining (T5)
Co-authored T5: a practical template for unified NLP training and evaluation.
Co-authored Gemma 2: improving open language models at a practical size.
Multimodal frontier models (Gemini)
Co-authored Gemini: A Family of Highly Capable Multimodal Models.
Instruction-following via RLHF (InstructGPT)
Important for the product-and-systems side of OpenAI because his work spans the lab’s robotics era and later instruction-following language-model work.
Open-weight frontier models (Llama 3)
Co-authored “The Llama 3 Herd of Models”.