Cover Image

KurTail : Kurtosis-based LLM Quantization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Akhondzadeh, Mohammad Sadegh, Bojchevski, Aleksandar, Eleftheriou, Evangelos, Dazzi, Martino
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Test-Time Training Undermines Safety Guardrails
by: Antonelli, Simone, et al.
Published: (2026)

One Sample is Enough to Make Conformal Prediction Robust
by: Zargarbashi, Soroush H., et al.
Published: (2025)

Robust Yet Efficient Conformal Prediction Sets
by: Zargarbashi, Soroush H., et al.
Published: (2024)

EvA: Evolutionary Attacks on Graphs
by: Akhondzadeh, Mohammad Sadegh, et al.
Published: (2025)

EfQAT: An Efficient Framework for Quantization-Aware Training
by: Ashkboos, Saleh, et al.
Published: (2024)

Conformal Inductive Graph Neural Networks
by: Zargarbashi, Soroush H., et al.
Published: (2024)

Robust Conformal Prediction with a Single Binary Certificate
by: Zargarbashi, Soroush H., et al.
Published: (2025)

SafePowerGraph: Safety-aware Evaluation of Graph Neural Networks for Transmission Power Grids
by: Ghamizi, Salah, et al.
Published: (2024)

Randomized Message-Interception Smoothing: Gray-box Certificates for Graph Neural Networks
by: Scholten, Yan, et al.
Published: (2023)

Localized Randomized Smoothing for Collective Robustness Certification
by: Schuchardt, Jan, et al.
Published: (2022)

Hierarchical Randomized Smoothing
by: Scholten, Yan, et al.
Published: (2023)

Optimal Conformal Prediction under Epistemic Uncertainty
by: Javanmardi, Alireza, et al.
Published: (2025)

Convolutional Neural Networks Towards Facial Skin Lesions Detection
by: Sarshar, Reza, et al.
Published: (2024)

A 1/R Law for Kurtosis Contrast in Balanced Mixtures
by: Bi, Yuda, et al.
Published: (2026)

Kurtosis-Guided Denoising Score Matching for Tabular Anomaly Detection
by: Livernoche, Victor, et al.
Published: (2026)

Sharp High-Probability Rates for Nonlinear SGD under Heavy-Tailed Noise via Symmetrization
by: Armacki, Aleksandar, et al.
Published: (2025)

Rethinking Residual Errors in Compensation-based LLM Quantization
by: Li, Shuaiting, et al.
Published: (2026)

On the Sample Complexity of Discounted Reinforcement Learning with Optimized Certainty Equivalents
by: Mortensen, Oliver, et al.
Published: (2026)

Tight Long-Term Tail Decay of (Clipped) SGD in Non-Convex Optimization
by: Armacki, Aleksandar, et al.
Published: (2026)

Beyond ROUGE: N-Gram Subspace Features for LLM Hallucination Detection
by: Li, Jerry, et al.
Published: (2025)

Graph Neural Networks and Reinforcement Learning for Proactive Application Image Placement
by: Makris, Antonios, et al.
Published: (2024)

Recursive Entropic Risk Optimization in Discounted MDPs: Sample Complexity Bounds with a Generative Model
by: Mortensen, Oliver, et al.
Published: (2025)

ACT-JEPA: Novel Joint-Embedding Predictive Architecture for Efficient Policy Representation Learning
by: Vujinovic, Aleksandar, et al.
Published: (2025)

FuseSampleAgg: Fused Neighbor Sampling and Aggregation for Mini-batch GNNs
by: Stanković, Aleksandar
Published: (2025)

ML-SpecQD: Multi-Level Speculative Decoding with Quantized Drafts
by: Georganas, Evangelos, et al.
Published: (2025)

Sampling from Energy-based Policies using Diffusion
by: Jain, Vineet, et al.
Published: (2024)

SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors
by: Lingam, Vijay, et al.
Published: (2024)

Randomized Least Squares Value Iteration itself is Joint Differentially Private
by: Lu, Haiyang, et al.
Published: (2026)

FPTQuant: Function-Preserving Transforms for LLM Quantization
by: van Breugel, Boris, et al.
Published: (2025)

Tail Annealing for Heavy-Tailed Flow Matching
by: Pachebat, Jean
Published: (2026)

From Bits to Chips: An LLM-based Hardware-Aware Quantization Agent for Streamlined Deployment of LLMs
by: Deng, Kaiyuan, et al.
Published: (2026)

How to Shrink Confidence Sets for Many Equivalent Discrete Distributions?
by: Maillard, Odalric-Ambrym, et al.
Published: (2024)

AutoSAGE: Input-Aware CUDA Scheduling for Sparse GNN Aggregation (SpMM/SDDMM) and CSR Attention
by: Stankovic, Aleksandar
Published: (2025)

SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compression
by: Mozaffari, Mohammad, et al.
Published: (2024)

BitSnap: Checkpoint Sparsification and Quantization in LLM Training
by: Peng, Yanxin, et al.
Published: (2025)

WUSH: Near-Optimal Adaptive Transforms for LLM Quantization
by: Chen, Jiale, et al.
Published: (2025)

Apertus LLM Family Expansion via Distillation and Quantization
by: Panferov, Andrei, et al.
Published: (2026)

Leech Lattice Vector Quantization for Efficient LLM Compression
by: van der Ouderaa, Tycho F. A., et al.
Published: (2026)

Hurwitz Quaternion Multiplicative Quantization for KV Cache Compression
by: Swain, Kabir, et al.
Published: (2026)

Exploiting LLM Quantization
by: Egashira, Kazuki, et al.
Published: (2024)