:: Library Catalog

Cover Image

Saved in:

Bibliographic Details
Main Authors:	Hu, Robert, Luschi, Carlo, Balanca, Paul
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	https://arxiv.org/abs/2509.17791
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Scalify: scale propagation for efficient low-precision LLM training
by: Balança, Paul, et al.
Published: (2024)

MXNorm: Reusing MXFP block scales for efficient tensor normalisation
by: McLean, Callum, et al.
Published: (2026)

Reducing the Cost of Quantum Chemical Data By Backpropagating Through Density Functional Theory
by: Mathiasen, Alexander, et al.
Published: (2024)

Optimal Formats for Weight Quantisation
by: Orr, Douglas, et al.
Published: (2025)

Ground-Truth Subgraphs for Better Training and Evaluation of Knowledge Graph Augmented LLMs
by: Cattaneo, Alberto, et al.
Published: (2025)

SparQ Attention: Bandwidth-Efficient LLM Inference
by: Ribar, Luka, et al.
Published: (2023)

Towards Efficient Pre-training: Exploring FP4 Precision in Large Language Models
by: Zhou, Jiecheng, et al.
Published: (2025)

Scaling FP8 training to trillion-token LLMs
by: Fishman, Maxim, et al.
Published: (2024)

Elucidating the Design Space of Dataset Condensation
by: Shao, Shitong, et al.
Published: (2024)

Efficient Post-training Quantization with FP8 Formats
by: Shen, Haihao, et al.
Published: (2023)

UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG
by: Georgiev, Dobrik, et al.
Published: (2026)

Elucidating the Design Space of Multimodal Protein Language Models
by: Hsieh, Cheng-Yen, et al.
Published: (2025)

Metis: Training LLMs with FP4 Quantization
by: Cao, Hengjie, et al.
Published: (2025)

Elucidating the Design Space of Arbitrary-Noise-Based Diffusion Models
by: Qiu, Xingyu, et al.
Published: (2025)

ETTA: Elucidating the Design Space of Text-to-Audio Models
by: Lee, Sang-gil, et al.
Published: (2024)

FP8-Flow-MoE: A Casting-Free FP8 Recipe without Double Quantization Error
by: Wang, Fengjuan, et al.
Published: (2025)

The Role of Graph Topology in the Performance of Biomedical Knowledge Graph Completion Models
by: Cattaneo, Alberto, et al.
Published: (2024)

$μ$nit Scaling: Simple and Scalable FP8 LLM Training
by: Narayan, Saaketh, et al.
Published: (2025)

Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization
by: Egiazarian, Vage, et al.
Published: (2025)

FP6-LLM: Efficiently Serving Large Language Models Through FP6-Centric Algorithm-System Co-Design
by: Xia, Haojun, et al.
Published: (2024)

FP8 Quantization: The Power of the Exponent
by: Kuzmin, Andrey, et al.
Published: (2022)

FP4 All the Way: Fully Quantized Training of LLMs
by: Chmiel, Brian, et al.
Published: (2025)

Quartet: Native FP4 Training Can Be Optimal for Large Language Models
by: Castro, Roberto L., et al.
Published: (2025)

ThriftAttention: Selective Mixed Precision for Long-Context FP4 Attention
by: Sharratt, Joe
Published: (2026)

Pretraining large language models with MXFP4 on Native FP4 Hardware
by: Cim, Musa, et al.
Published: (2026)

Elucidating the Design Choice of Probability Paths in Flow Matching for Forecasting
by: Lim, Soon Hoe, et al.
Published: (2024)

Optimizing Large Language Model Training Using FP4 Quantization
by: Wang, Ruizhe, et al.
Published: (2025)

The Curse and Blessing of Mean Bias in FP4-Quantized LLM Training
by: Cao, Hengjie, et al.
Published: (2026)

u-$μ$P: The Unit-Scaled Maximal Update Parametrization
by: Blake, Charlie, et al.
Published: (2024)

An Inquiry into Datacenter TCO for LLM Inference with FP8
by: Kim, Jiwoo, et al.
Published: (2025)

Towards Fully FP8 GEMM LLM Training at Scale
by: Hernández-Cano, Alejandro, et al.
Published: (2025)

When Flat Minima Fail: Characterizing INT4 Quantization Collapse After FP32 Convergence
by: Armstrong, Marcus
Published: (2026)

FP-AbDiff: Improving Score-based Antibody Design by Capturing Nonequilibrium Dynamics through the Underlying Fokker-Planck Equation
by: Chen, Jiameng, et al.
Published: (2025)

Practical FP4 Training for Large-Scale MoE Models on Hopper GPUs
by: Zhang, Wuyue, et al.
Published: (2026)

FireQ: Fast INT4-FP8 Kernel and RoPE-aware Quantization for LLM Inference Acceleration
by: Baek, Daehyeon, et al.
Published: (2025)

Accelerating Transformer Pre-training with 2:4 Sparsity
by: Hu, Yuezhou, et al.
Published: (2024)

COMET:Combined Matrix for Elucidating Targets
by: Wang, Haojie, et al.
Published: (2024)

Design Space Exploration of Approximate Computing Techniques with a Reinforcement Learning Approach
by: Saeedi, Sepide, et al.
Published: (2023)

Targeted Adaptive Design
by: Graziani, Carlo, et al.
Published: (2022)

Defeating the Training-Inference Mismatch via FP16
by: Qi, Penghui, et al.
Published: (2025)