RB
Ron Banner
cs.LGcs.CVcs.AIstat.MLcs.CLcs.DCcs.IRcs.PF
On Valency
published · living versionsW_f2a7whhj·v1 · currentpublished
Dory1.0-4B: A Looped Normalized-GPT
with Maxim Fishman, Simeng Sun, Shantanu Acharya, Faisal Ladhak +4
1 version
Preprints & journals
26 papers in the corpus · 2018–2026UNREAL: Unifying Retrieval and Long-Context with a Single Model2610.08463v1 · Edan Kinderman, Elad Hoffer, Yochai Blau et al.2026 · 0 citationsarXiv
Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning2606.15007v1 · NVIDIA: Aaron Blakeman, Aaron Thomas, Aastha Jhunjhunwala et al.2026 · 0 citationsarXiv
Workspace Optimization: How to Train Your Agent2605.09650v1 · Elad Sarafian, Gal Kaplun, Ron Banner et al.2026 · 0 citationsarXiv
Retrieval from Within: An Intrinsic Capability of Attention-Based Models2605.05806v3 · Elad Hoffer, Yochai Blau, Edan Kinderman et al.2026 · 0 citationsarXiv
Normalized Architectures are Natively 4-Bit2605.06067v1 · Maxim Fishman, Brian Chmiel, Ron Banner et al.2026 · 0 citationsarXiv
Distributed Training under Packet Loss2507.07114v1 · Erez Weintraub, Ron Banner, Ariel Orda2025 · 0 citationsarXiv
FP4 All the Way: Fully Quantized Training of LLMs2505.19115v2 · Brian Chmiel, Maxim Fishman, Ron Banner et al.2025 · 1 citationarXiv
EXAQ: Exponent Aware Quantization For LLMs Acceleration2410.03185v1 · Moran Shkolnik, Maxim Fishman, Brian Chmiel et al.2024 · 0 citationsarXiv
Scaling FP8 training to trillion-token LLMs2409.12517v2 · Maxim Fishman, Brian Chmiel, Ron Banner et al.2024 · 1 citationarXiv
DropCompute: simple and more robust distributed synchronous training via compute variance reduction2306.10598v2 · Niv Giladi, Shahar Gottlieb, Moran Shkolnik et al.2023 · 0 citations37th Conference on Neural Information Processing Systems (NeurIPS 2023)
Minimum Variance Unbiased N:M Sparsity for the Neural Gradients2203.10991v3 · Brian Chmiel, Itay Hubara, Ron Banner et al.2022 · 2 citationsarXiv
Energy awareness in low precision neural networks2202.02783v1 · Nurit Spingarn Eliezer, Ron Banner, Elad Hoffer et al.2022 · 0 citationsarXiv
Graph Representation Learning via Aggregation Enhancement2201.12843v4 · Maxim Fishman, Chaim Baskin, Evgenii Zheltonozhskii et al.2022 · 0 citationsarXiv
Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats2112.10769v4 · Brian Chmiel, Ron Banner, Elad Hoffer et al.2021 · 6 citationsarXiv
Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N:M Transposable Masks2102.08124v2 · Itay Hubara, Brian Chmiel, Moshe Island et al.2021 · 36 citationsarXiv
GAN "Steerability" without optimization2012.05328v2 · Nurit Spingarn-Eliezer, Ron Banner, Tomer Michaeli2020 · 20 citationsarXiv
Neural gradients are near-lognormal: improved quantized and sparse training2006.08173v3 · Brian Chmiel, Liad Ben-Uri, Moran Shkolnik et al.2020 · 17 citationsarXiv
Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming2006.10518v2 · Itay Hubara, Yury Nahshan, Yair Hanani et al.2020 · 77 citationsarXiv
Robust Quantization: One Model to Rule Them All2002.07686v3 · Moran Shkolnik, Brian Chmiel, Ron Banner et al.2020 · 47 citationsarXiv
Loss Aware Post-training Quantization1911.07190v2 · Yury Nahshan, Brian Chmiel, Chaim Baskin et al.2019 · 154 citationsarXiv
CAT: Compression-Aware Training for bandwidth reduction1909.11481v1 · Chaim Baskin, Brian Chmiel, Evgenii Zheltonozhskii et al.2019 · 11 citationsarXiv
Thanks for Nothing: Predicting Zero-Valued Activations with Lightweight Convolutional Neural Networks1909.07636v3 · Gil Shomron, Ron Banner, Moran Shkolnik et al.2019 · 23 citationsarXiv
Feature Map Transform Coding for Energy-Efficient CNN Inference1905.10830v3 · Brian Chmiel, Chaim Baskin, Ron Banner et al.2019 · 24 citationsarXiv
Post-training 4-bit quantization of convolution networks for rapid-deployment1810.05723v3 · Ron Banner, Yury Nahshan, Elad Hoffer et al.2018 · 115 citationsarXiv
Scalable Methods for 8-bit Training of Neural Networks1805.11046v3 · Ron Banner, Itay Hubara, Elad Hoffer et al.2018 · 184 citationsarXiv
Norm matters: efficient and accurate normalization schemes in deep networks1803.01814v3 · Elad Hoffer, Ron Banner, Itay Golan et al.2018 · 102 citationsNeurIPS2018
Career total: 47 works. 26 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.