No article text was recorded for this version.
weight oscillation
Version 1 of 135 papers45 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Overcoming Oscillations in Quantization-Aware Training
- Blog: One-Step Forward and Backtrack: Overcoming Zig-Zagging in Loss-Aware Quantization Training
- Blog: Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precision
- Blog: Reducing the Side-Effects of Oscillations in Training of Quantized YOLO Networks
- Blog: Retraining-free Model Quantization via One-Shot Weight-Coupling Learning
- Blog: Oscillation-free Quantization for Low-bit Vision Transformers
- Blog: Learnable Companding Quantization for Accurate Low-Bit Neural Networks
- Blog: Toward Efficient Low-Precision Training: Data Format Optimization and Hysteresis Quantization
- Blog: Oscillation-Reduced MXFP4 Training for Vision Transformers
- Blog: FLIQS: One-Shot Mixed-Precision Floating-Point and Integer Quantization Search
- Blog: Optimal Clipping and Magnitude-aware Differentiation for Improved Quantization-aware Training
- Blog: Merge-Friendly Post-Training Quantization for Multi-Target Domain Adaptation
- Blog: Preserve then Quantize: Dominant-Subspace Guided Low-Rank Reconstruction
- Blog: Exploring Quantization for Efficient Pre-Training of Transformer Language Models
- Blog: Memory Efficient Optimizers with 4-bit States
- Blog: Resilient Binary Neural Network
- Blog: SA-BNN: State-Aware Binary Neural Network
- Blog: Bayesian Optimized 1-Bit CNNs
- Blog: BHViT: Binarized Hybrid Vision Transformer
- Blog: Uncertainty-aware Binary Neural Networks
- Blog: Training Binary Neural Networks through Learning with Noisy Supervision
- Blog: Overcoming Oscillations in Quantization-Aware Training
- Blog: Towards Vector Optimization on Low-Dimensional Vector Symbolic Architecture
- Blog: How to Train a Compact Binary Neural Network with High Accuracy?
- Blog: Once Quantization-Aware Training: High Performance Extremely Low-bit Architecture Search
- Blog: ProxQuant: Quantized Neural Networks via Proximal Operators
- Blog: BSO: Binary Spiking Online Optimization Algorithm
- Blog: Towards Accurate Binary Spiking Neural Networks: Learning with Adaptive Gradient Modulation Mechanism
- Blog: DenseShift : Towards Accurate and Efficient Low-Bit Power-of-Two Quantization
- Blog: TetraJet-v2: Accurate NVFP4 Training for Large Language Models with Oscillation Suppression and Outlier Control
- Blog: Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural Networks
- Blog: Search What You Want: Barrier Panelty NAS for Mixed Precision Quantization
- Blog: Matryoshka Quantization
- Blog: Genie: Show Me the Data for Quantization
- Blog: PROFIT: A Novel Training Method for sub-4-bit MobileNet Models
History & citation
Current · Permanent link
- This direction split from Suppressing Weight Oscillation for Stable Low Precision Training (51% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_weight_oscillation_78f3d4cf,
title = {weight oscillation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/weight-oscillation/rdr_78f3d4cf8dab488aa555cfe198738469},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_weight_oscillation_78f3d4cf_v1,
title = {weight oscillation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/weight-oscillation/rdr_78f3d4cf8dab488aa555cfe198738469/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}