Imagen de Portada

Affine-Scaled Attention: Towards Flexible and Stable Transformer Attention

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Bae, Jeongin, Park, Baeseong, Park, Gunho, Kim, Minsub, Lee, Joonhyung, Yoo, Junhee, Woo, Sunghyeon, Ryu, Jiwon, Kwon, Se Jung, Lee, Dongsoo
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

CodeGEMM: A Codebook-Centric Approach to Efficient GEMM in Quantized LLMs
por: Park, Gunho, et al.
Publicado: (2025)

AnyBCQ: Hardware Efficient Flexible Binary-Coded Quantization for Multi-Precision LLMs
por: Park, Gunho, et al.
Publicado: (2025)

FIGLUT: An Energy-Efficient Accelerator Design for FP-INT GEMM Using Look-Up Tables
por: Park, Gunho, et al.
Publicado: (2025)

SelfJudge: Faster Speculative Decoding via Self-Supervised Judge Verification
por: Yoon, Kanghoon, et al.
Publicado: (2025)

LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models
por: Park, Gunho, et al.
Publicado: (2022)

To FP8 and Back Again: Quantifying Reduced Precision Effects on LLM Training Stability
por: Lee, Joonhyung, et al.
Publicado: (2024)

ICaRus: Identical Cache Reuse for Efficient Multi Model Inference
por: Woo, Sunghyeon, et al.
Publicado: (2026)

DropBP: Accelerating Fine-Tuning of Large Language Models by Dropping Backward Propagation
por: Woo, Sunghyeon, et al.
Publicado: (2024)

Training-free Dropout Sampling for Semantic Token Acceptance in Speculative Decoding
por: Lee, Jeongtae, et al.
Publicado: (2026)

An Inquiry into Datacenter TCO for LLM Inference with FP8
por: Kim, Jiwoo, et al.
Publicado: (2025)

SUN: Shared Use of Next-token Prediction for Efficient Multi-LLM Disaggregated Serving
por: Woo, Sunghyeon, et al.
Publicado: (2026)

No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization
por: Yang, June Yong, et al.
Publicado: (2024)

PrefillShare: A Shared Prefill Module for KV Reuse in Multi-LLM Disaggregated Serving
por: Woo, Sunghyeon, et al.
Publicado: (2026)

Unifying Uniform and Binary-coding Quantization for Accurate Compression of Large Language Models
por: Park, Seungcheol, et al.
Publicado: (2025)

Faster Inference of LLMs using FP8 on the Intel Gaudi
por: Lee, Joonhyung, et al.
Publicado: (2025)

FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization
por: Lee, Jung Hyun, et al.
Publicado: (2023)

Attention-Based Reading, Highlighting, and Forecasting of the Limit Order Book
por: Jung, Jiwon, et al.
Publicado: (2024)

LRQ: Optimizing Post-Training Quantization for Large Language Models by Learning Low-Rank Weight-Scaling Matrices
por: Lee, Jung Hyun, et al.
Publicado: (2024)

Debunking the CUDA Myth Towards GPU-based AI Systems
por: Lee, Yunjae, et al.
Publicado: (2024)

Rethinking Channel Dimensions to Isolate Outliers for Low-bit Weight Quantization of Large Language Models
por: Heo, Jung Hwan, et al.
Publicado: (2023)

Attention-aware Semantic Communications for Collaborative Inference
por: Im, Jiwoong, et al.
Publicado: (2024)

Organic Ferroelectrics for Regulation of Electronic and Ionic Transport Toward Neuromorphic Applications
por: Minsub Lee, et al.
Publicado: (2024)

BioArtlas: Mapping Bioart's Polysemy with an Embedding-Derived Lexicon
por: Bae, Joonhyung
Publicado: (2025)

BioArtlas: Computational Clustering of Multi‑Dimensional Complexity in Bioart
por: Bae, Joonhyung
Publicado: (2025)

BioArtlas: Computational Clustering of Multi-Dimensional Complexity in Bioart
por: Bae, Joonhyung
Publicado: (2025)

ASTRA: Mapping Art-Technology Institutions via Conceptual Axes, Text Embeddings, and Unsupervised Clustering
por: Bae, Joonhyung
Publicado: (2026)

Thief of Truth: VR comics about the relationship between AI and humans
por: Bae, Joonhyung
Publicado: (2025)

Amanous: Distribution-Switching for Superhuman Piano Density on Disklavier
por: Bae, Joonhyung
Publicado: (2026)

Addressing Low E/S and N/P Ratio Challenges in Li–S Batteries with a Multifunctional Interlayer
por: Cinthya Paulina, et al.
Publicado: (2026)

RaDL: Relation-aware Disentangled Learning for Multi-Instance Text-to-Image Generation
por: Park, Geon, et al.
Publicado: (2025)

Visual Preference Inference: An Image Sequence-Based Preference Reasoning in Tabletop Object Manipulation
por: Lee, Joonhyung, et al.
Publicado: (2024)

Where to invest? Effects of technological capabilities on corporate venture capital investments
por: Wonsang Ryu, et al.
Publicado: (2024)

MimiQ: Low-Bit Data-Free Quantization of Vision Transformers with Encouraging Inter-Head Attention Similarity
por: Choi, Kanghyun, et al.
Publicado: (2024)

Unveiling the Response of Large Vision-Language Models to Visually Absent Tokens
por: Kim, Sohee, et al.
Publicado: (2025)

Watermarking for Factuality: Guiding Vision-Language Models Toward Truth via Tri-layer Contrastive Decoding
por: Back, Kyungryul, et al.
Publicado: (2025)

Physical Containers as Framing Conditions for Visualization in Augmented Reality
por: Bae, Jiyeon, et al.
Publicado: (2026)

Serial Quantitative Evaluation of Load Redistribution and Osteotomy Gap After Medial Open‐Wedge High Tibial Osteotomy
por: Jae Woo Cho, et al.
Publicado: (2025)

LampQ: Towards Accurate Layer-wise Mixed Precision Quantization for Vision Transformers
por: Kim, Minjun, et al.
Publicado: (2025)

PAFormer: Part Aware Transformer for Person Re-identification
por: Jung, Hyeono, et al.
Publicado: (2024)

QFlash: Bridging Quantization and Memory Efficiency in Vision Transformer Attention
por: Oh, Sehyeon, et al.
Publicado: (2026)