IEEE

Practical and Flexible Backdoor Attack Against Deep Learning Models via Shell Code Injection

Abstract: Recently, backdoor attack, which aims to implant malicious logic into deep learning models (DLMs), has attracted so extensive research attention. Among them, the non-poisoning-based backdoor ...
GitHub

Diffusion Language Models are Super Data Learners

[2025-10-27] We release the codebase, all training checkpoints, and logs. The codebase is highly optimized and is industry-level in terms scalability and efficiency. [2025-10-03] The full paper is out ...
GitHub

GPU-optimized framework for training diffusion language models at any scale.

Comprehensive Training Pipelines: Full support for Diffusion Language Models (DLMs) and Autoregressive LMs, from pre-training and SFT to RL, on both dense and MoE architectures. We strongly recommend ...
IEEE

Continuous Cuffless Blood Pressure Estimation via Effective and Efficient Broad Learning Model

Abstract: Hypertension is a major risk factor for cardiovascular diseases and all-cause mortality, making accessible and easy blood pressure (BP) measurement, such as cuffless methods, crucial for its ...