Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kennedy, Ian W., Moosavi, Nafise Sadat
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Deconstructing Attention: Investigating Design Principles for Effective Language Modeling
par: Xue, Huiyin, et autres
Publié: (2025)

More or Less Wrong: A Benchmark for Directional Bias in LLM Comparative Reasoning
par: Shafiei, Mohammadamin, et autres
Publié: (2025)

How to Leverage Digit Embeddings to Represent Numbers?
par: Sivakumar, Jasivan Alex, et autres
Publié: (2024)

AAAC: Activation-Aware Adaptive Codebooks for 4-bit LLM Weight Quantization
par: IslamBouli, Beshr, et autres
Publié: (2026)

MultiHoax: A Dataset of Multi-hop False-Premise Questions
par: Shafiei, Mohammadamin, et autres
Publié: (2025)

LLMs as Narcissistic Evaluators: When Ego Inflates Evaluation Scores
par: Liu, Yiqi, et autres
Publié: (2023)

Rolling the DICE on Idiomaticity: How LLMs Fail to Grasp Context
par: Mi, Maggie, et autres
Publié: (2024)

From Input Perception to Predictive Insight: Modeling Model Blind Spots Before They Become Errors
par: Mi, Maggie, et autres
Publié: (2025)

Exploring the Influence of Label Aggregation on Minority Voices: Implications for Dataset Bias and Model Training
par: Pandya, Mugdha, et autres
Publié: (2024)

QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks
par: Tseng, Albert, et autres
Publié: (2024)

Decoding News Narratives: A Critical Analysis of Large Language Models in Framing Detection
par: Pastorino, Valeria, et autres
Publié: (2024)

LCQ: Low-Rank Codebook based Quantization for Large Language Models
par: Cai, Wen-Pu, et autres
Publié: (2024)

QAM-W: Joint 2D Codebook Quantization for LLM Weights via Hadamard Rotation and Activation-Aware Scaling
par: Sharma, Preetam, et autres
Publié: (2026)

No Shortcuts to Culture: Indonesian Multi-hop Question Answering for Complex Cultural Understanding
par: Permadi, Vynska Amalia, et autres
Publié: (2026)

Faithful Summarisation under Disagreement via Belief-Level Aggregation
par: Aghaebe, Favour Yahdii, et autres
Publié: (2026)

LLMs Do Not See Age: Assessing Demographic Bias in Automated Systematic Review Synthesis
par: Aghaebe, Favour Yahdii, et autres
Publié: (2025)

Highly Optimized Kernels and Fine-Grained Codebooks for LLM Inference on Arm CPUs
par: Gope, Dibakar, et autres
Publié: (2024)

DartQuant: Efficient Rotational Distribution Calibration for LLM Quantization
par: Shao, Yuantian, et autres
Publié: (2025)

SqueezeLLM: Dense-and-Sparse Quantization
par: Kim, Sehoon, et autres
Publié: (2023)

CRVQ: Channel-Relaxed Vector Quantization for Extreme Compression of LLMs
par: Xu, Yuzhuang, et autres
Publié: (2024)

Extreme Compression of Large Language Models via Additive Quantization
par: Egiazarian, Vage, et autres
Publié: (2024)

RIGOURATE: Quantifying Scientific Exaggeration with Evidence-Aligned Claim Evaluation
par: James, Joseph, et autres
Publié: (2026)

Beyond Hate Speech: NLP's Challenges and Opportunities in Uncovering Dehumanizing Language
par: Saffari, Hamidreza, et autres
Publié: (2024)

GPTVQ: The Blessing of Dimensionality for LLM Quantization
par: van Baalen, Mart, et autres
Publié: (2024)

Exploring Gender Disparities in Automatic Speech Recognition Technology
par: ElGhazaly, Hend, et autres
Publié: (2025)

BlockDialect: Block-wise Fine-grained Mixed Format Quantization for Energy-Efficient LLM Inference
par: Jang, Wonsuk, et autres
Publié: (2025)

ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization
par: Liu, Zechun, et autres
Publié: (2025)

FlatQuant: Flatness Matters for LLM Quantization
par: Sun, Yuxuan, et autres
Publié: (2024)

ContrastScore: Towards Higher Quality, Less Biased, More Efficient Evaluation Metrics with Contrastive Evaluation
par: Wang, Xiao, et autres
Publié: (2025)

Hidden Failures in Robustness: Why Supervised Uncertainty Quantification Needs Better Evaluation
par: Stacey, Joe, et autres
Publié: (2026)

Revisiting Adaptive Rounding with Vectorized Reparameterization for LLM Quantization
par: Zhou, Yuli, et autres
Publié: (2026)

QEFT: Quantization for Efficient Fine-Tuning of LLMs
par: Lee, Changhun, et autres
Publié: (2024)

Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook
par: Lee, Jaehyeok, et autres
Publié: (2026)

QUAD: Quantization and Parameter-Efficient Tuning of LLM with Activation Decomposition
par: Hu, Yuxuan, et autres
Publié: (2025)

Exposing Pink Slime Journalism: Linguistic Signatures and Robust Detection Against LLM-Generated Threats
par: Shahriar, Sadat, et autres
Publié: (2025)

Faster MoE LLM Inference for Extremely Large Models
par: Yang, Haoqi, et autres
Publié: (2025)

Semantic Codebooks as Effective Priors for Neural Speech Compression
par: Bai, Liuyang, et autres
Publié: (2025)

Zebra-Llama: Towards Extremely Efficient Hybrid Models
par: Yang, Mingyu, et autres
Publié: (2025)

AMAQ: Adaptive Mixed-bit Activation Quantization for Collaborative Parameter Efficient Fine-tuning
par: Song, Yurun, et autres
Publié: (2025)

Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation
par: Eger, Steffen, et autres
Publié: (2025)