Cover Image

A Training-free Sub-quadratic Cost Transformer Model Serving Framework With Hierarchically Pruned Attention

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lee, Heejun, Park, Geon, Lee, Youngwan, Suh, Jaduk, Kim, Jina, Jeong, Wonyoung, Kim, Bumsik, Lee, Hyemin, Jeon, Myeongjae, Hwang, Sung Ju
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Computer Vision and Pattern Recognition Distributed, Parallel, and Cluster Computing Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU
by: Lee, Heejun, et al.
Published: (2025)

Training-Free Exponential Context Extension via Cascading KV Cache
by: Willette, Jeffrey, et al.
Published: (2024)

SEA: Sparse Linear Attention with Estimated Attention Mask
by: Lee, Heejun, et al.
Published: (2023)

VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding
by: Kim, Kangsan, et al.
Published: (2024)

Visualizing the loss landscape of Self-supervised Vision Transformer
by: Lee, Youngwan, et al.
Published: (2024)

EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens
by: Hwang, Sunil, et al.
Published: (2022)

KOALA: Empirical Lessons Toward Memory-Efficient and Fast Diffusion Models for Text-to-Image Synthesis
by: Lee, Youngwan, et al.
Published: (2023)

MultihopSpatial: Multi-hop Compositional Spatial Reasoning Benchmark for Vision-Language Model
by: Lee, Youngwan, et al.
Published: (2026)

HoliSafe: Holistic Safety Benchmarking and Modeling for Vision-Language Model
by: Lee, Youngwan, et al.
Published: (2025)

GFlowPO: Generative Flow Network as a Language Model Prompt Optimizer
by: Cho, Junmo, et al.
Published: (2026)

MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied Agents
by: Kim, Kangsan, et al.
Published: (2026)

K/DA: Automated Data Generation Pipeline for Detoxifying Implicitly Offensive Language in Korean
by: Jeon, Minkyeong, et al.
Published: (2025)

SIA: Enhancing Safety via Intent Awareness for Vision-Language Models
by: Na, Youngjin, et al.
Published: (2025)

Position as Probability: Self-Supervised Transformers that Think Past Their Training for Length Extrapolation
by: Lee, Philip Heejun
Published: (2025)

PawPrint: Whose Footprints Are These? Identifying Animal Individuals by Their Footprints
by: Song, Inpyo, et al.
Published: (2025)

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation
by: Lim, Hyemin, et al.
Published: (2025)

DiTTO-LLM: Framework for Discovering Topic-based Technology Opportunities via Large Language Model
by: Kim, Wonyoung, et al.
Published: (2025)

REP: Resource-Efficient Prompting for Rehearsal-Free Continual Learning
by: Jeon, Sungho, et al.
Published: (2024)

Your Thoughtful Opponent: Embracing Cognitive Conflict with Peer Agent
by: Kim, Kyuwon, et al.
Published: (2025)

Toward Cost-Efficient Serving of Mixture-of-Experts with Asynchrony
by: Wang, Shaoyu, et al.
Published: (2025)

Automatic Channel Pruning for Multi-Head Attention
by: Lee, Eunho, et al.
Published: (2024)

SDS KoPub VDR: A Benchmark Dataset for Visual Document Retrieval in Korean Public Documents
by: Lee, Jaehoon, et al.
Published: (2025)

Dynamic and Super-Personalized Media Ecosystem Driven by Generative AI: Unpredictable Plays Never Repeating The Same
by: Ahn, Sungjun, et al.
Published: (2024)

HEISIR: Hierarchical Expansion of Inverted Semantic Indexing for Training-free Retrieval of Conversational Data using LLMs
by: Kim, Sangyeop, et al.
Published: (2025)

Divide and Translate: Compositional First-Order Logic Translation and Verification for Complex Logical Reasoning
by: Ryu, Hyun, et al.
Published: (2024)

FineScope : SAE-guided Data Selection Enables Domain Specific LLM Pruning and Finetuning
by: Bhattacharyya, Chaitali, et al.
Published: (2025)

Exploring Hierarchical Consistency and Unbiased Objectness for Open-Vocabulary Object Detection
by: Lee, Sanghoon, et al.
Published: (2026)

STELLA: Continual Audio-Video Pre-training with Spatio-Temporal Localized Alignment
by: Lee, Jaewoo, et al.
Published: (2023)

ReviewScore: Misinformed Peer Review Detection with Large Language Models
by: Ryu, Hyun, et al.
Published: (2025)

Amuse: Human-AI Collaborative Songwriting with Multimodal Inspirations
by: Kim, Yewon, et al.
Published: (2024)

Preference-Aligned LoRA Merging: Preserving Subspace Coverage and Addressing Directional Anisotropy
by: Jeong, Wooseong, et al.
Published: (2026)

Label-Free Cross-Task LoRA Merging with Null-Space Compression
by: Lee, Wonyoung, et al.
Published: (2026)

OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources
by: Baek, Jinheon, et al.
Published: (2026)

VideoRAG: Retrieval-Augmented Generation over Video Corpus
by: Jeong, Soyeong, et al.
Published: (2025)

Everyday Physics in Korean Contexts: A Culturally Grounded Physical Reasoning Benchmark
by: Jeong, Jihae, et al.
Published: (2025)

LG AI Research & KAIST at EHRSQL 2024: Self-Training Large Language Models with Pseudo-Labeled Unanswerable Questions for a Reliable Text-to-SQL System on EHRs
by: Jo, Yongrae, et al.
Published: (2024)

DOO-RE: A dataset of ambient sensors in a meeting room for activity recognition
by: Kim, Hyunju, et al.
Published: (2024)

Distilling LLM Agent into Small Models with Retrieval and Code Tools
by: Kang, Minki, et al.
Published: (2025)

Rethinking Saliency-Guided Weakly-Supervised Semantic Segmentation
by: Kim, Beomyoung, et al.
Published: (2024)

A More Word-like Image Tokenization for MLLMs
by: Lee, Hyun, et al.
Published: (2026)