18 citations · 20 across the 14 of their papers we have counts for
15 papers
RIFT: KV Cache Compression for Draft Models with Complementary Compressibility Training
Dor Tsur, Maor Ashkenazi, Maximilian Golub +7
Speculative decoding is a popular decode acceleration method. As such, it is particularly relevant to long-output generation, which requires an increasingly large KV cache. KV cach…
LiLiCorr: Lightweight Likelihood Correlation of Parallel Drafts for Speculative Decoding
Matan Rusanovsky, Yoav Miron, Roy Uziel +5
Speculative decoding accelerates language-model inference by drafting future tokens the target model verifies in parallel. A diffusion-style drafter such as DFlash drafts an entire…
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…
Cybersecurity is the True Frontier for Generative AI Success or Failure
Edward Raff, Maor Ashkenazi, Sagar Samtani +2
Cybersecurity is a real-life test-bed for many machine learning problems at once, especially when considering modern strides in using Large Language Models (LLMs) to automate proce…
Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
NVIDIA, :, Aaron Blakeman +572
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…
SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding
Talor Abramovich, Maor Ashkenazi, Izzy Putterman +5
Speculative Decoding (SD) has emerged as a critical technique for accelerating Large Language Model (LLM) inference. Unlike deterministic system optimizations, SD performance is in…
Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding
Hayate Iso, Tiyasa Mitra, Sudipta Mondal +15
RL post-training of frontier language models is increasingly bottlenecked by autoregressive rollout generation, making rollout acceleration a central systems challenge. Many existi…
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…
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…
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…
Zero-Shot Detection of LLM-Generated Code via Approximated Task Conditioning
Maor Ashkenazi, Ofir Brenner, Tal Furman Shohet +1
Detecting Large Language Model (LLM)-generated code is a growing challenge with implications for security, intellectual property, and academic integrity. We investigate the role of…
A New Dataset and Methodology for Malicious URL Classification
Ilan Schvartzman, Roei Sarussi, Maor Ashkenazi +3
Malicious URL (Uniform Resource Locator) classification is a pivotal aspect of Cybersecurity, offering defense against web-based threats. Despite deep learning's promise in this ar…
Towards Croppable Implicit Neural Representations
Maor Ashkenazi, Eran Treister
Implicit Neural Representations (INRs) have peaked interest in recent years due to their ability to encode natural signals using neural networks. While INRs allow for useful applic…
NeRN -- Learning Neural Representations for Neural Networks
Maor Ashkenazi, Zohar Rimon, Ron Vainshtein +4
Neural Representations have recently been shown to effectively reconstruct a wide range of signals from 3D meshes and shapes to images and videos. We show that, when adapted correc…
Wavelet Feature Maps Compression for Image-to-Image CNNs
Shahaf E. Finder, Yair Zohav, Maor Ashkenazi +1
Convolutional Neural Networks (CNNs) are known for requiring extensive computational resources, and quantization is among the best and most common methods for compressing them. Whi…