Author

Dun-Li Chan

3 papers indexed here

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.

#machine learning Review Oct 2026

Shared Geometry Is Not Shared Physics: A Layerwise Test of the Platonic Representation Hypothesis in Astronomy

In this paper we investigate whether geometrically aligned astronomical representations are also scientifically interchangeable. We analyze every layer's representation from 36 pretrained models using cross-matched optical images, infrared images, and spectra. All 139 analyzed model-survey comparisons show significant...

Kshitij Duraphe, A. Kannappan, Dun-Li Chan et al. · 0 citations

Preprint Aug 2026

Do All LLMs Know When They're Being Harmful? A Reproducibility Study of Latent-Space Safety Probes Across Model Families

Khatri et al. (2026) [DOI: 10.1109/DSN-W70714.2026.00027] show that lightweight MLP probes on final-layer activations of a single 8B model (LLaMA-3.1-8B) detect harmful prompts at F1 competitive with guard models 1000x larger, using one probe per benchmark. We reproduce this pipeline end-to-end and extend it along two...

Alizishaan Khatri, Dun-Li Chan · 2 citations

#natural language process... Preprint Sep 2026

How Perturbations Propagate: A Multi-Level Analysis of Robustness in Large Language Models

The results show that robustness claims based on a single behavioral or representational metric can be misleading, and motivate multi-level evaluation of how perturbations alter language-model computation.

Dun-Li Chan, Emily Liu, Niyathi Allu et al. · 0 citations