Copertina

Activation Quantization of Vision Encoders Needs Prefixing Registers

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kim, Seunghyeon, Yeom, Taesun, Kim, Jinho, Park, Wonpyo, Kim, Kyuyeun, Lee, Jaeho
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Prefixing Attention Sinks can Mitigate Activation Outliers for Large Language Model Quantization
di: Son, Seungwoo, et al.
Pubblicazione: (2024)

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

ZIP: An Efficient Zeroth-order Prompt Tuning for Black-box Vision-Language Models
di: Park, Seonghwan, et al.
Pubblicazione: (2025)

MetaMix: Meta-state Precision Searcher for Mixed-precision Activation Quantization
di: Kim, Han-Byul, et al.
Pubblicazione: (2023)

Edge-case Synthesis for Fisheye Object Detection: A Data-centric Perspective
di: Kim, Seunghyeon, et al.
Pubblicazione: (2025)

Neural Image Compression with Text-guided Encoding for both Pixel-level and Perceptual Fidelity
di: Lee, Hagyeong, et al.
Pubblicazione: (2024)

Diffusion-based Data Augmentation and Knowledge Distillation with Generated Soft Labels Solving Data Scarcity Problems of SAR Oil Spill Segmentation
di: Moon, Jaeho, et al.
Pubblicazione: (2024)

In Search of a Data Transformation That Accelerates Neural Field Training
di: Seo, Junwon, et al.
Pubblicazione: (2023)

Discovering and Mitigating Visual Biases through Keyword Explanation
di: Kim, Younghyun, et al.
Pubblicazione: (2023)

HLQ: Fast and Efficient Backpropagation via Hadamard Low-rank Quantization
di: Kim, Seonggon, et al.
Pubblicazione: (2024)

PTQ4VM: Post-Training Quantization for Visual Mamba
di: Cho, Younghyun, et al.
Pubblicazione: (2024)

Instance-Aware Group Quantization for Vision Transformers
di: Moon, Jaehyeon, et al.
Pubblicazione: (2024)

On the Internal Representations of Graph Metanetworks
di: Yeom, Taesun, et al.
Pubblicazione: (2025)

The Role of Masking for Efficient Supervised Knowledge Distillation of Vision Transformers
di: Son, Seungwoo, et al.
Pubblicazione: (2023)

Merge-Friendly Post-Training Quantization for Multi-Target Domain Adaptation
di: Shin, Juncheol, et al.
Pubblicazione: (2025)

Do VLMs Need Vision Transformers? Evaluating State Space Models as Vision Encoders
di: Kuo, Shang-Jui Ray, et al.
Pubblicazione: (2026)

Test-Time Training for Visual Foresight Vision-Language-Action Models
di: Park, Sangwu, et al.
Pubblicazione: (2026)

Preserving Pre-trained Representation Space: On Effectiveness of Prefix-tuning for Large Multi-modal Models
di: Kim, Donghoon, et al.
Pubblicazione: (2024)

Stabilizing Consistency Training: A Flow Map Analysis and Self-Distillation
di: Kim, Youngjoong, et al.
Pubblicazione: (2026)

MoSSDA: A Semi-Supervised Domain Adaptation Framework for Multivariate Time-Series Classification using Momentum Encoder
di: Kim, Seonyoung, et al.
Pubblicazione: (2025)

FedWSQ: Efficient Federated Learning with Weight Standardization and Distribution-Aware Non-Uniform Quantization
di: Kim, Seung-Wook, et al.
Pubblicazione: (2025)

Decoupling Augmentation Bias in Prompt Learning for Vision-Language Models
di: Kim, Gahyeon, et al.
Pubblicazione: (2025)

AAPL: Adding Attributes to Prompt Learning for Vision-Language Models
di: Kim, Gahyeon, et al.
Pubblicazione: (2024)

Maximizing the Position Embedding for Vision Transformers with Global Average Pooling
di: Lee, Wonjun, et al.
Pubblicazione: (2025)

Bi-MCQ: Reformulating Vision-Language Alignment for Negation Understanding
di: Kim, Tae Hun, et al.
Pubblicazione: (2026)

Multi-frame Restoration for High-rate Lissajous Confocal Laser Endomicroscopy
di: Lee, Minhee, et al.
Pubblicazione: (2026)

Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models
di: Lee, Jeongjae, et al.
Pubblicazione: (2026)

Leveraging Registers in Vision Transformers for Robust Adaptation
di: Yellapragada, Srikar, et al.
Pubblicazione: (2025)

Rethinking the Use of Vision Transformers for AI-Generated Image Detection
di: Park, NaHyeon, et al.
Pubblicazione: (2025)

Efficient LLaMA-3.2-Vision by Trimming Cross-attended Visual Features
di: Lee, Jewon, et al.
Pubblicazione: (2025)

TempCore: Are Video QA Benchmarks Temporally Grounded? A Frame Selection Sensitivity Analysis and Benchmark
di: Ok, Hyunjong, et al.
Pubblicazione: (2025)

Erase at the Core: Representation Unlearning for Machine Unlearning
di: Lee, Jaewon, et al.
Pubblicazione: (2026)

Decoder-Free Distillation for Quantized Image Restoration
di: Sharif, S. M. A., et al.
Pubblicazione: (2026)

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

Probabilistic Precision and Recall Towards Reliable Evaluation of Generative Models
di: Park, Dogyun, et al.
Pubblicazione: (2023)

TailedCore: Few-Shot Sampling for Unsupervised Long-Tail Noisy Anomaly Detection
di: Jung, Yoon Gyo, et al.
Pubblicazione: (2025)

Consistency-Preserving Concept Erasure via Unsafe-Safe Pairing and Directional Fisher-weighted Adaptation
di: Kim, Yongwoo, et al.
Pubblicazione: (2026)

Diffusion-Based Offline RL for Improved Decision-Making in Augmented ARC Task
di: Kim, Yunho, et al.
Pubblicazione: (2024)

AcTTA: Rethinking Test-Time Adaptation via Dynamic Activation
di: Kim, Hyeongyu, et al.
Pubblicazione: (2026)

Soft Equivariance Regularization for Invariant Self-Supervised Learning
di: Lee, Joohyung, et al.
Pubblicazione: (2026)