Image de couverture de livre

ReSpinQuant: Efficient Layer-Wise LLM Quantization via Subspace Residual Rotation Approximation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kim, Suyoung, Wee, Sunghyun, Kim, Hyeonjin, Hwang, Kyomin, Lee, Hyunho, Kwak, Nojun
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Safety-Preserving PTQ via Contrastive Alignment Loss
par: Wee, Sunghyun, et autres
Publié: (2025)

Uncovering the Potential Risks in Unlearning: Danger of English-only Unlearning in Multilingual LLMs
par: Hwang, Kyomin, et autres
Publié: (2025)

Knowledge Beyond Language: Bridging the Gap in Multilingual Machine Unlearning Evaluation
par: Hwang, Kyomin, et autres
Publié: (2026)

Do not think about pink elephant!
par: Hwang, Kyomin, et autres
Publié: (2024)

Deep Support Vectors
par: Lee, Junhoo, et autres
Publié: (2024)

Retrieval-Augmented Generation Based Nurse Observation Extraction
par: Hwang, Kyomin, et autres
Publié: (2026)

Unlocking the Potential of Unlabeled Data in Semi-Supervised Domain Generalization
par: Lee, Dongkwan, et autres
Publié: (2025)

Any-Way Meta Learning
par: Lee, Junhoo, et autres
Publié: (2024)

The Role of Teacher Calibration in Knowledge Distillation
par: Kim, Suyoung, et autres
Publié: (2025)

Practical Dataset Distillation Based on Deep Support Vectors
par: Lee, Hyunho, et autres
Publié: (2024)

Mitigating the Bias in the Model for Continual Test-Time Adaptation
par: Chung, Inseop, et autres
Publié: (2024)

Coreset Selection for Object Detection
par: Lee, Hojun, et autres
Publié: (2024)

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

Unlocking the Potential of Diffusion Language Models through Template Infilling
par: Lee, Junhoo, et autres
Publié: (2025)

Deep Edge Filter: Return of the Human-Crafted Layer in Deep Learning
par: Lee, Dongkwan, et autres
Publié: (2025)

ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference
par: Liang, Yesheng, et autres
Publié: (2025)

Kinematic Modulation in Driven Spin Resonance
par: Kim, Sunghyun
Publié: (2026)

Singular Value Scaling: Efficient Generative Model Compression via Pruned Weights Refinement
par: Kim, Hyeonjin, et autres
Publié: (2024)

ReFlex: Text-Guided Editing of Real Images in Rectified Flow via Mid-Step Feature Extraction and Attention Adaptation
par: Kim, Jimyeong, et autres
Publié: (2025)

From Local to Global to Mechanistic: An iERF-Centered Unified Framework for Interpreting Vision Models
par: Kim, Yearim, et autres
Publié: (2026)

Respect the model: Fine-grained and Robust Explanation with Sharing Ratio Decomposition
par: Han, Sangyu, et autres
Publié: (2024)

Causal Interpretation of Sparse Autoencoder Features in Vision
par: Han, Sangyu, et autres
Publié: (2025)

PedaCo-Gen: Scaffolding Pedagogical Agency in Human-AI Collaborative Video Authoring
par: Baek, Injun, et autres
Publié: (2026)

PolarQuant: Optimal Gaussian Weight Quantization via Hadamard Rotation for LLM Compression
par: Vicentino, Caio
Publié: (2026)

A Revisit to the Decoder for Camouflaged Object Detection
par: Ko, Seung Woo, et autres
Publié: (2025)

Style Composition within Distinct LoRA modules for Traditional Art
par: Lee, Jaehyun, et autres
Publié: (2025)

Toward Structural Multimodal Representations: Specialization, Selection, and Sparsification via Mixture-of-Experts
par: Choi, Hahyeon, et autres
Publié: (2026)

CSF: Black-box Fingerprinting via Compositional Semantics for Text-to-Image Models
par: Lee, Junhoo, et autres
Publié: (2026)

NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models
par: Chong, Hyochan, et autres
Publié: (2026)

Are LLM-Judges Robust to Expressions of Uncertainty? Investigating the effect of Epistemic Markers on LLM-based Evaluation
par: Lee, Dongryeol, et autres
Publié: (2024)

FibQuant: Universal Vector Quantization for Random-Access KV-Cache Compression
par: Lee, Namyoon, et autres
Publié: (2026)

Can You Trick the Grader? Adversarial Persuasion of LLM Judges
par: Hwang, Yerin, et autres
Publié: (2025)

MERLIN: Multimodal Embedding Refinement via LLM-based Iterative Navigation for Text-Video Retrieval-Rerank Pipeline
par: Han, Donghoon, et autres
Publié: (2024)

MASQ: Accelerating Masked Diffusion via Stage-Wise Multi-Precision Quantization
par: Kim, Seeyeon, et autres
Publié: (2026)

Conservative Generator, Progressive Discriminator: Coordination of Adversaries in Few-shot Incremental Image Synthesis
par: Kong, Chaerin, et autres
Publié: (2022)

What's Making That Sound Right Now? Video-centric Audio-Visual Localization
par: Choi, Hahyeon, et autres
Publié: (2025)

Decompose the model: Mechanistic interpretability in image models with Generalized Integrated Gradients (GIG)
par: Kim, Yearim, et autres
Publié: (2024)

Multi-dimensional Preference Alignment by Conditioning Reward Itself
par: Jang, Jiho, et autres
Publié: (2025)

Subspace-based Approximate Hessian Method for Zeroth-Order Optimization
par: Kim, Dongyoon, et autres
Publié: (2025)

Efficient Generative Modeling with Residual Vector Quantization-Based Tokens
par: Kim, Jaehyeon, et autres
Publié: (2024)