Cover Image

Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ma, Lianbo, Ma, Jianlun, Zhou, Yuee, Xie, Guoyang, He, Qiang, Lu, Zhichao
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

One-Step Forward and Backtrack: Overcoming Zig-Zagging in Loss-Aware Quantization Training
by: Ma, Lianbo, et al.
Published: (2024)

Revisiting Multimodal Fusion for 3D Anomaly Detection from an Architectural Perspective
by: Long, Kaifang, et al.
Published: (2024)

Towards an Incremental Unified Multimodal Anomaly Detection: Augmenting Multimodal Denoising From an Information Bottleneck Perspective
by: Long, Kaifang, et al.
Published: (2026)

Where and How to Enhance: Discovering Bit-Width Contribution for Mixed Precision Quantization
by: Kang, Haidong, et al.
Published: (2025)

MoQAE: Mixed-Precision Quantization for Long-Context LLM Inference via Mixture of Quantization-Aware Experts
by: Tao, Wei, et al.
Published: (2025)

Adaptively Sampling-Reusing-Mixing Decomposed Gradients to Speed Up Sharpness Aware Minimization
by: Deng, Jiaxin, et al.
Published: (2025)

Rethinking Unsupervised Outlier Detection via Multiple Thresholding
by: Liu, Zhonghang, et al.
Published: (2024)

ShadowMaskFormer: Mask Augmented Patch Embeddings for Shadow Removal
by: Li, Zhuohao, et al.
Published: (2024)

Modality-Aware SAM: Sharpness-Aware-Minimization Driven Gradient Modulation for Harmonized Multimodal Learning
by: Nowdeh, Hossein R., et al.
Published: (2025)

Adaptive Distribution-aware Quantization for Mixed-Precision Neural Networks
by: Jia, Shaohang, et al.
Published: (2025)

Towards Zero-shot Point Cloud Anomaly Detection: A Multi-View Projection Framework
by: Cheng, Yuqi, et al.
Published: (2024)

Adaptive Dataset Quantization
by: Li, Muquan, et al.
Published: (2024)

Value-Driven Mixed-Precision Quantization for Patch-Based Inference on Microcontrollers
by: Tao, Wei, et al.
Published: (2024)

Precision Neural Network Quantization via Learnable Adaptive Modules
by: Zhou, Wenqiang, et al.
Published: (2025)

Reframing Long-Tailed Learning via Loss Landscape Geometry
by: Chen, Shenghan, et al.
Published: (2026)

FairQuant: Fairness-Aware Mixed-Precision Quantization for Medical Image Classification
by: Woergaard, Thomas, et al.
Published: (2026)

SARD: Segmentation-Aware Anomaly Synthesis via Region-Constrained Diffusion with Discriminative Mask Guidance
by: Wang, Yanshu, et al.
Published: (2025)

Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model
by: Ranjan, Navin, et al.
Published: (2025)

HEP-NAS: Towards Efficient Few-shot Neural Architecture Search via Hierarchical Edge Partitioning
by: Li, Jianfeng, et al.
Published: (2024)

Vision-Language Semantic Aggregation Leveraging Foundation Model for Generalizable Medical Image Segmentation
by: Yu, Wenjun, et al.
Published: (2025)

Mix-QViT: Mixed-Precision Vision Transformer Quantization Driven by Layer Importance and Quantization Sensitivity
by: Ranjan, Navin, et al.
Published: (2025)

Sharpness-Aware Data Generation for Zero-shot Quantization
by: Hoang-Anh, Dung, et al.
Published: (2025)

Jumping through Local Minima: Quantization in the Loss Landscape of Vision Transformers
by: Frumkin, Natalia, et al.
Published: (2023)

AnomalyXFusion: Multi-modal Anomaly Synthesis with Diffusion
by: Hu, Jie, et al.
Published: (2024)

TreeQ: Pushing the Quantization Boundary of Diffusion Transformer via Tree-Structured Mixed-Precision Search
by: Yang, Kaicheng, et al.
Published: (2025)

Pre-Trained LLM is a Semantic-Aware and Generalizable Segmentation Booster
by: Tang, Fenghe, et al.
Published: (2025)

STAGE: Segmentation-oriented Industrial Anomaly Synthesis via Graded Diffusion with Explicit Mask Alignment
by: Xu, Xichen, et al.
Published: (2025)

DynaQuant: Dynamic Mixed-Precision Quantization for Learned Image Compression
by: Bao, Youneng, et al.
Published: (2025)

Gradient-Aligned Calibration for Post-Training Quantization of Diffusion Models
by: Hoang, Dung Anh, et al.
Published: (2026)

Data-Free Quantization via Mixed-Precision Compensation without Fine-Tuning
by: Chen, Jun, et al.
Published: (2023)

AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning
by: Huang, Duojun, et al.
Published: (2024)

Retraining-free Model Quantization via One-Shot Weight-Coupling Learning
by: Tang, Chen, et al.
Published: (2024)

MPQ-Diff: Mixed Precision Quantization for Diffusion Models
by: Maruzzelli, Rocco Manz, et al.
Published: (2024)

FAST: Foreground-aware Diffusion with Accelerated Sampling Trajectory for Segmentation-oriented Anomaly Synthesis
by: Xu, Xichen, et al.
Published: (2025)

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation
by: Huang, Qing, et al.
Published: (2026)

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

Aligned Contrastive Loss for Long-Tailed Recognition
by: Ma, Jiali, et al.
Published: (2025)

LRP-QViT: Mixed-Precision Vision Transformer Quantization via Layer-wise Relevance Propagation
by: Ranjan, Navin, et al.
Published: (2024)

ActAvatar: Temporally-Aware Precise Action Control for Talking Avatars
by: Peng, Ziqiao, et al.
Published: (2025)

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