No official code found. Best implementation: AntigoneRandy/QCB-LACPDA (12 stars, Apache-2.0, last commit 2024-08-14).
Instance-wise Batch Label Restoration via Gradients in Federated Learning
Planning, Fast and Slow: Online Reinforcement Learning with Action-Free Offline Data via Multiscale Planners
R*: Efficient Reward Design via Reward Structure Evolution and Parameter Alignment Optimization with Large Language Models
True Knowledge Comes from Practice: Aligning Large Language Models with Embodied Environments via Reinforcement Learning
Connecting Pre-trained Language Model and Downstream Task via Properties of Representation
Dual-Perspective Activation: Efficient Channel Denoising via Joint Forward-Backward Criterion for Artificial Neural Networks
@article{li2026purifying,
title = {Purifying Quantization-conditioned Backdoors via Layer-wise Activation Correction with Distribution Approximation},
author = {Boheng Li and Yishuo Cai and Jisong Cai and Yiming Li and Han Qiu and Run Wang and Tianwei Zhang},
year = {2026},
url = {https://api.semanticscholar.org/CorpusID:0dd744d859e049e20f44505cee330fbce85102c4},
journal = {ICML 2024 2024}
}Shows whether official code is linked for this paper.
[](https://codeofpaper.com/paper/0dd744d859e049e20f44505cee330fbce85102c4)