papers

Publications (13)

cs.LG2025

Puzzle: Distillation-Based NAS for Inference-Optimized LLMs

Akhiad Bercovich, Tomer Ronen, Talor Abramovich +23

Large language models (LLMs) offer remarkable capabilities, yet their high inference costs restrict wider adoption. While increasing parameter counts improves accuracy, it also bro…

cs.LG2026

Extending Puzzle for Mixture-of-Experts Reasoning Models with Application to GPT-OSS Acceleration

Akhiad Bercovich, Nir Ailon, Vladimir Anisimov +21

Reasoning-focused LLMs improve answer quality by generating longer reasoning traces, but the additional tokens dramatically increase serving cost, motivating inference optimization…

cs.LG2026

Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

NVIDIA, :, Aakshita Chandiramani +544

We describe the pre-training, post-training, and quantization of Nemotron 3 Super, a 120 billion (active 12 billion) parameter hybrid Mamba-Attention Mixture-of-Experts model. Nemo…

cs.CL2025

NVIDIA Nemotron 3: Efficient and Open Intelligence

NVIDIA, :, Aaron Blakeman +356

We introduce the Nemotron 3 family of models - Nano, Super, and Ultra. These models deliver strong agentic, reasoning, and conversational capabilities. The Nemotron 3 family uses a…

cs.AI2026

Nemotron-Labs-3-Puzzle-75B-A9B: Compressing Hybrid MoE LLMs

Akhiad Bercovich, Talor Abramovich, Daniel Afrimi +67

We present Nemotron-Labs-3-Puzzle-75B-A9B, a compressed variant of Nemotron-3-Super optimized for interactive deployment. We designed the model to maximize server throughput under…

cs.CL2026

Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

NVIDIA, :, Aaron Blakeman +571

We introduce Nemotron 3 Ultra, a 550 billion total and 55 billion active parameter Mixture-of-Experts Hybrid Mamba-Attention language model. We pre-trained Nemotron 3 Ultra on 20 t…

cs.CL2025

Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

NVIDIA, :, Aaron Blakeman +311

We present Nemotron 3 Nano 30B-A3B, a Mixture-of-Experts hybrid Mamba-Transformer language model. Nemotron 3 Nano was pretrained on 25 trillion text tokens, including more than 3 t…

cs.LG2025

FFN Fusion: Rethinking Sequential Computation in Large Language Models

Akhiad Bercovich, Mohammad Dabbah, Omri Puny +15

We introduce FFN Fusion, an architectural optimization technique that reduces sequential computation in large language models by identifying and exploiting natural opportunities fo…

cs.LG2019

ML for Flood Forecasting at Scale

Sella Nevo, Vova Anisimov, Gal Elidan +11

Effective riverine flood forecasting at scale is hindered by a multitude of factors, most notably the need to rely on human calibration in current methodology, the limited amount o…

cs.LG2021

Flood forecasting with machine learning models in an operational framework

Sella Nevo, Efrat Morin, Adi Gerzi Rosenthal +28

The operational flood forecasting system by Google was developed to provide accurate real-time flood warnings to agencies and the public, with a focus on riverine floods in large,…

cs.CL2025

Llama-Nemotron: Efficient Reasoning Models

Akhiad Bercovich, Itay Levy, Izik Golan +132

We introduce the Llama-Nemotron series of models, an open family of heterogeneous reasoning models that deliver exceptional reasoning capabilities, inference efficiency, and an ope…

cs.LG2020

HydroNets: Leveraging River Structure for Hydrologic Modeling

Zach Moshe, Asher Metzger, Gal Elidan +3

Accurate and scalable hydrologic models are essential building blocks of several important applications, from water resource management to timely flood warnings. However, as the cl…

cs.LG2019

Towards Global Remote Discharge Estimation: Using the Few to Estimate The Many

Yotam Gigi, Gal Elidan, Avinatan Hassidim +5

Learning hydrologic models for accurate riverine flood prediction at scale is a challenge of great importance. One of the key difficulties is the need to rely on in-situ river disc…