Image de couverture de livre

LAQuant: A Simple Overhead-free Large Reasoning Model Quantization by Layer-wise Lookahead Loss

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Choi, Euntae, Song, Sumin, Yoo, Sungjoo
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Rotate, Clip, and Partition: Towards W2A4KV4 Quantization by Integrating Rotation and Learnable Non-uniform Quantizer
par: Choi, Euntae, et autres
Publié: (2025)

Grouped Sequency-arranged Rotation: Optimizing Rotation Transformation for Quantization for Free
par: Choi, Euntae, et autres
Publié: (2025)

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache
par: Son, Donghyun, et autres
Publié: (2025)

Phys3DGS: Physically-based 3D Gaussian Splatting for Inverse Rendering
par: Choi, Euntae, et autres
Publié: (2024)

Gaussian Weight Sampling for Scalable, Efficient and Stable Pseudo-Quantization Training
par: Ahn, Myeonghwan, et autres
Publié: (2025)

Baking Relightable NeRF for Real-time Direct/Indirect Illumination Rendering
par: Choi, Euntae, et autres
Publié: (2024)

Layer-wise Quantization for Quantized Optimistic Dual Averaging
par: Nguyen, Anh Duc, et autres
Publié: (2025)

LoaQ: Layer-wise Output Approximation Quantization
par: Lin, Li, et autres
Publié: (2025)

On the Effect of Uncertainty on Layer-wise Inference Dynamics
par: Kim, Sunwoo, et autres
Publié: (2025)

MetaMix: Meta-state Precision Searcher for Mixed-precision Activation Quantization
par: Kim, Han-Byul, et autres
Publié: (2023)

Scaling Speculative Decoding with Lookahead Reasoning
par: Fu, Yichao, et autres
Publié: (2025)

Exploring Layer-wise Information Effectiveness for Post-Training Quantization in Small Language Models
par: Xiao, He, et autres
Publié: (2025)

Causal Attention with Lookahead Keys
par: Song, Zhuoqing, et autres
Publié: (2025)

A Few Large Shifts: Layer-Inconsistency Based Minimal Overhead Adversarial Example Detection
par: Yun, Sanggeon, et autres
Publié: (2025)

GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance
par: Kim, Jinuk, et autres
Publié: (2025)

R2 Loss: Range Restriction Loss for Model Compression and Quantization
par: Kundu, Arnav, et autres
Publié: (2023)

Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss
par: Park, Sangyeon, et autres
Publié: (2025)

Iterative Layer-wise Distillation for Efficient Compression of Large Language Models
par: Kovalev, Grigory, et autres
Publié: (2025)

MergeQuant: Accurate 4-bit Static Quantization of Large Language Models by Channel-wise Calibration
par: Wang, Jinguang, et autres
Publié: (2025)

Determining Layer-wise Sparsity for Large Language Models Through a Theoretical Perspective
par: Huang, Weizhong, et autres
Publié: (2025)

Next-Depth Lookahead Tree
par: Lee, Jaeho, et autres
Publié: (2025)

Reinforcement Learning with Lookahead Information
par: Merlis, Nadav
Publié: (2024)

Generalization and Optimization of SGD with Lookahead
par: Li, Kangcheng, et autres
Publié: (2025)

Lookahead Drifting Model
par: Zhang, Guoqiang, et autres
Publié: (2026)

The Impact of Quantization on Large Reasoning Model Reinforcement Learning
par: Kumar, Medha, et autres
Publié: (2025)

Disentangling Recall and Reasoning in Transformer Models through Layer-wise Attention and Activation Analysis
par: Fartale, Harshwardhan, et autres
Publié: (2025)

Lookahead Counterfactual Fairness
par: Zuo, Zhiqun, et autres
Publié: (2024)

Scalable Model Merging with Progressive Layer-wise Distillation
par: Xu, Jing, et autres
Publié: (2025)

QTALE: Quantization-Robust Token-Adaptive Layer Execution for LLMs
par: Noh, Kanghyun, et autres
Publié: (2026)

The Value of Reward Lookahead in Reinforcement Learning
par: Merlis, Nadav, et autres
Publié: (2024)

Layer-wise Derivative Controlled Networks
par: Martnishn, Rowan, et autres
Publié: (2026)

Layer-wise Linear Mode Connectivity
par: Adilova, Linara, et autres
Publié: (2023)

Low-Complexity Semantic Packet Aggregation for Token Communication via Lookahead Search
par: Lee, Seunghun, et autres
Publié: (2025)

A Convex-optimization-based Layer-wise Post-training Pruner for Large Language Models
par: Zhao, Pengxiang, et autres
Publié: (2024)

Rethinking Layer-wise Model Merging through Chain of Merges
par: Buzzega, Pietro, et autres
Publié: (2025)

Policy Mirror Descent with Lookahead
par: Protopapas, Kimon, et autres
Publié: (2024)

Adaptive Layer-Wise Transformations for Post-Training Quantization of Large Language Models
par: Pham, Cuong, et autres
Publié: (2025)

Tequila: Trapping-free Ternary Quantization for Large Language Models
par: Huang, Hong, et autres
Publié: (2025)

QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead
par: Zandieh, Amir, et autres
Publié: (2024)

Lookahead: An Inference Acceleration Framework for Large Language Model with Lossless Generation Accuracy
par: Zhao, Yao, et autres
Publié: (2023)