Cover Image

Initialisation Determines the Basin: Efficient Codebook Optimisation for Extreme LLM Quantization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kennedy, Ian W., Moosavi, Nafise Sadat
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Deconstructing Attention: Investigating Design Principles for Effective Language Modeling
by: Xue, Huiyin, et al.
Published: (2025)

More or Less Wrong: A Benchmark for Directional Bias in LLM Comparative Reasoning
by: Shafiei, Mohammadamin, et al.
Published: (2025)

How to Leverage Digit Embeddings to Represent Numbers?
by: Sivakumar, Jasivan Alex, et al.
Published: (2024)

AAAC: Activation-Aware Adaptive Codebooks for 4-bit LLM Weight Quantization
by: IslamBouli, Beshr, et al.
Published: (2026)

MultiHoax: A Dataset of Multi-hop False-Premise Questions
by: Shafiei, Mohammadamin, et al.
Published: (2025)

LLMs as Narcissistic Evaluators: When Ego Inflates Evaluation Scores
by: Liu, Yiqi, et al.
Published: (2023)

Rolling the DICE on Idiomaticity: How LLMs Fail to Grasp Context
by: Mi, Maggie, et al.
Published: (2024)

From Input Perception to Predictive Insight: Modeling Model Blind Spots Before They Become Errors
by: Mi, Maggie, et al.
Published: (2025)

Exploring the Influence of Label Aggregation on Minority Voices: Implications for Dataset Bias and Model Training
by: Pandya, Mugdha, et al.
Published: (2024)

QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks
by: Tseng, Albert, et al.
Published: (2024)

Decoding News Narratives: A Critical Analysis of Large Language Models in Framing Detection
by: Pastorino, Valeria, et al.
Published: (2024)

LCQ: Low-Rank Codebook based Quantization for Large Language Models
by: Cai, Wen-Pu, et al.
Published: (2024)

QAM-W: Joint 2D Codebook Quantization for LLM Weights via Hadamard Rotation and Activation-Aware Scaling
by: Sharma, Preetam, et al.
Published: (2026)

No Shortcuts to Culture: Indonesian Multi-hop Question Answering for Complex Cultural Understanding
by: Permadi, Vynska Amalia, et al.
Published: (2026)

Faithful Summarisation under Disagreement via Belief-Level Aggregation
by: Aghaebe, Favour Yahdii, et al.
Published: (2026)

LLMs Do Not See Age: Assessing Demographic Bias in Automated Systematic Review Synthesis
by: Aghaebe, Favour Yahdii, et al.
Published: (2025)

Highly Optimized Kernels and Fine-Grained Codebooks for LLM Inference on Arm CPUs
by: Gope, Dibakar, et al.
Published: (2024)

DartQuant: Efficient Rotational Distribution Calibration for LLM Quantization
by: Shao, Yuantian, et al.
Published: (2025)

SqueezeLLM: Dense-and-Sparse Quantization
by: Kim, Sehoon, et al.
Published: (2023)

CRVQ: Channel-Relaxed Vector Quantization for Extreme Compression of LLMs
by: Xu, Yuzhuang, et al.
Published: (2024)

Extreme Compression of Large Language Models via Additive Quantization
by: Egiazarian, Vage, et al.
Published: (2024)

RIGOURATE: Quantifying Scientific Exaggeration with Evidence-Aligned Claim Evaluation
by: James, Joseph, et al.
Published: (2026)

Beyond Hate Speech: NLP's Challenges and Opportunities in Uncovering Dehumanizing Language
by: Saffari, Hamidreza, et al.
Published: (2024)

GPTVQ: The Blessing of Dimensionality for LLM Quantization
by: van Baalen, Mart, et al.
Published: (2024)

Exploring Gender Disparities in Automatic Speech Recognition Technology
by: ElGhazaly, Hend, et al.
Published: (2025)

BlockDialect: Block-wise Fine-grained Mixed Format Quantization for Energy-Efficient LLM Inference
by: Jang, Wonsuk, et al.
Published: (2025)

ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization
by: Liu, Zechun, et al.
Published: (2025)

ContrastScore: Towards Higher Quality, Less Biased, More Efficient Evaluation Metrics with Contrastive Evaluation
by: Wang, Xiao, et al.
Published: (2025)

FlatQuant: Flatness Matters for LLM Quantization
by: Sun, Yuxuan, et al.
Published: (2024)

Hidden Failures in Robustness: Why Supervised Uncertainty Quantification Needs Better Evaluation
by: Stacey, Joe, et al.
Published: (2026)

Revisiting Adaptive Rounding with Vectorized Reparameterization for LLM Quantization
by: Zhou, Yuli, et al.
Published: (2026)

QEFT: Quantization for Efficient Fine-Tuning of LLMs
by: Lee, Changhun, et al.
Published: (2024)

Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook
by: Lee, Jaehyeok, et al.
Published: (2026)

QUAD: Quantization and Parameter-Efficient Tuning of LLM with Activation Decomposition
by: Hu, Yuxuan, et al.
Published: (2025)

Exposing Pink Slime Journalism: Linguistic Signatures and Robust Detection Against LLM-Generated Threats
by: Shahriar, Sadat, et al.
Published: (2025)

Faster MoE LLM Inference for Extremely Large Models
by: Yang, Haoqi, et al.
Published: (2025)

Semantic Codebooks as Effective Priors for Neural Speech Compression
by: Bai, Liuyang, et al.
Published: (2025)

Zebra-Llama: Towards Extremely Efficient Hybrid Models
by: Yang, Mingyu, et al.
Published: (2025)

AMAQ: Adaptive Mixed-bit Activation Quantization for Collaborative Parameter Efficient Fine-tuning
by: Song, Yurun, et al.
Published: (2025)

Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation
by: Eger, Steffen, et al.
Published: (2025)