SynQ: Accurate Zero-shot Quantization by Synthesis-aware Fine-tuning
Minjun Kim, Jongjin Kim, U. Kang
2/12/2026
No official code found. Best implementation: snudm-starlab/SynQ (26 stars, Apache-2.0, last commit 2025-02-07).
Code Implementations(1)
Similar Papers
One Meta-tuned Transformer is What You Need for Few-shot Learning
91% match2026
Evaluating the Zero-shot Robustness of Instruction-tuned Language Models
91% match1 repo72026
Uncertainty-aware Fine-tuning of Segmentation Foundation Models
86% match1 repo162026
Skill-aware Mutual Information Optimisation for Zero-shot Generalisation in Reinforcement Learning
85% match2026
SaRA: High-Efficient Diffusion Model Fine-tuning with Progressive Sparse Low-Rank Adaptation
84% match1 repo1202026
Adjoint Matching: Fine-tuning Flow and Diffusion Generative Models with Memoryless Stochastic Optimal Control
83% match2026
Cite this paper
@article{kim2026synq,
title = {SynQ: Accurate Zero-shot Quantization by Synthesis-aware Fine-tuning},
author = {Minjun Kim and Jongjin Kim and U. Kang},
year = {2026},
url = {https://api.semanticscholar.org/CorpusID:68ed36758f66ad9ad372b27fe346330a0ac5e8b4},
journal = {ICLR 2025 2025}
}Add a badge to your README
Shows whether official code is linked for this paper.
[](https://codeofpaper.com/paper/68ed36758f66ad9ad372b27fe346330a0ac5e8b4)