Imagen de Portada

TWEO: Transformers Without Extreme Outliers Enables FP8 Training And Quantization For Dummies

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Liang, Guang, Shao, Jie, Tang, Ningyuan, Liu, Xinyao, Wu, Jianxin
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Computer Vision and Pattern Recognition Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Colinearity Decay: Training Quantization-Friendly ViTs with Outlier Decay
por: Tong, Jin, et al.
Publicado: (2026)

GPLQ: A General, Practical, and Lightning QAT Method for Vision Transformers
por: Liang, Guang, et al.
Publicado: (2025)

QwT-v2: Practical, Effective and Efficient Post-Training Quantization
por: Tang, Ningyuan, et al.
Publicado: (2025)

Nonlinear Bipolar Compensation: Handling Outliers in Post-Training Quantization
por: Sun, Peilin, et al.
Publicado: (2026)

Diffusion Product Quantization
por: Shao, Jie, et al.
Publicado: (2024)

Minimal Interaction Separated Tuning: A New Paradigm for Visual Adaptation
por: Tang, Ningyuan, et al.
Publicado: (2024)

LLM-FP4: 4-Bit Floating-Point Quantized Transformers
por: Liu, Shih-yang, et al.
Publicado: (2023)

YOLOv8-SMOT: An Efficient and Robust Framework for Real-Time Small Object Tracking via Slice-Assisted Training and Adaptive Association
por: Yu, Xiang, et al.
Publicado: (2025)

DuQuant++: Fine-grained Rotation Enhances Microscaling FP4 Quantization
por: Lin, Haokun, et al.
Publicado: (2026)

Quantization without Tears
por: Fu, Minghao, et al.
Publicado: (2024)

DopQ-ViT: Towards Distribution-Friendly and Outlier-Aware Post-Training Quantization for Vision Transformers
por: Yang, Lianwei, et al.
Publicado: (2024)

Image Outlier Detection Without Training using RANSAC
por: Tsai, Chen-Han, et al.
Publicado: (2023)

CHAOS: Chart Analysis with Outlier Samples
por: Moured, Omar, et al.
Publicado: (2025)

Outlier-Aware Post-Training Quantization for Image Super-Resolution
por: Wang, Hailing, et al.
Publicado: (2025)

FP4DiT: Towards Effective Floating Point Quantization for Diffusion Transformers
por: Chen, Ruichen, et al.
Publicado: (2025)

Low-rank Attention Side-Tuning for Parameter-Efficient Fine-Tuning
por: Tang, Ningyuan, et al.
Publicado: (2024)

FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusion
por: Liu, Akide, et al.
Publicado: (2025)

VLMQ: Token Saliency-Driven Post-Training Quantization for Vision-language Models
por: Xue, Yufei, et al.
Publicado: (2025)

HawkEye: Training Video-Text LLMs for Grounding Text in Videos
por: Wang, Yueqian, et al.
Publicado: (2024)

Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge
por: Wang, Yuxuan, et al.
Publicado: (2024)

Transformer-VQ: Linear-Time Transformers via Vector Quantization
por: Lingle, Lucas D.
Publicado: (2023)

HQ-DiT: Efficient Diffusion Transformer with FP4 Hybrid Quantization
por: Liu, Wenxuan, et al.
Publicado: (2024)

Perception Without Engagement: Dissecting the Causal Discovery Deficit in LMMs
por: Liang, Jiafeng, et al.
Publicado: (2026)

End-to-End Video Question Answering with Frame Scoring Mechanisms and Adaptive Sampling
por: Liang, Jianxin, et al.
Publicado: (2024)

ReasVQA: Advancing VideoQA with Imperfect Reasoning Process
por: Liang, Jianxin, et al.
Publicado: (2025)

Enhancing Post-Training Quantization via Future Activation Awareness
por: Lv, Zheqi, et al.
Publicado: (2026)

AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer
por: Wu, Zhuguanyu, et al.
Publicado: (2024)

Beyond Isolated Facts: Synthesizing Narrative and Grounded Supervision for VideoQA
por: Liang, Jianxin, et al.
Publicado: (2025)

VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format
por: Wang, Yueqian, et al.
Publicado: (2024)

Subject or Style: Adaptive and Training-Free Mixture of LoRAs
por: Zhang, Jia-Chen, et al.
Publicado: (2025)

Efficient Autoregressive Video Diffusion with Dummy Head
por: Guo, Hang, et al.
Publicado: (2026)

QuantDemoire: Quantization with Outlier Aware for Image Demoiréing
por: Chen, Zheng, et al.
Publicado: (2025)

DiffuLT: How to Make Diffusion Model Useful for Long-tail Recognition
por: Shao, Jie, et al.
Publicado: (2024)

ESsEN: Training Compact Discriminative Vision-Language Transformers in a Low-Resource Setting
por: Fields, Clayton, et al.
Publicado: (2026)

A Similarity Paradigm Through Textual Regularization Without Forgetting
por: Cui, Fangming, et al.
Publicado: (2025)

Getting More Juice Out of Your Data: Hard Pair Refinement Enhances Visual-Language Models Without Extra Data
por: Wang, Haonan, et al.
Publicado: (2023)

Post-Training Quantization for Diffusion Transformer via Hierarchical Timestep Grouping
por: Ding, Ning, et al.
Publicado: (2025)

From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models
por: Wu, Juncheng, et al.
Publicado: (2026)

Beyond Real Weights: Hypercomplex Representations for Stable Quantization
por: Ahad, Jawad Ibn, et al.
Publicado: (2025)

MPTQ-ViT: Mixed-Precision Post-Training Quantization for Vision Transformer
por: Tai, Yu-Shan, et al.
Publicado: (2024)