Author

Daniel Agyei Asante

h-index 1 View on Semantic Scholar

We have 2 of 7 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

Augmentation-Guided Adversarial Training via Local Stability-Based Sample Selection

Adversarial training remains one of the most effective defenses against adversarial attacks, but its standard PGD-based training is computationally expensive because adversarial examples are generated for every training sample. Selective adversarial training reduces this cost by perturbing only a subset of samples. How...

Daniel Agyei Asante, M. Tetteh, Deborah Asamoah et al. · 0 citations

#machine learning Preprint Aug 2026

TopoCompress: Long Context Compression via Graph-Wired Semantic Trajectories

TopoCompress is introduced, a training-free and model-agnostic framework that compresses long contexts by selecting coherent semantic spans by selecting coherent semantic spans and achieves performance comparable to the strongest baseline while using a 4x smaller compression budget.

Daniel Agyei Asante, Yang Li · 1 citation