2 papers
cs.CL2026
PALS: Percentile-Aware Layerwise Sparsity for LLM Pruning
Yazdan Jamshidi, Alexey Shvets
One-shot pruning methods like Wanda and SparseGPT apply the same sparsity ratio to every layer of a transformer, ignoring known variation in layer importance. We propose PALS (Perc…
cs.CR2026
Talk is (Not) Cheap: A Taxonomy and Benchmark Coverage Audit for LLM Attacks
Karthik Raghu Iyer, Yazdan Jamshidi, Nicholas Bray +1
We introduce a reusable framework for auditing whether LLM attack benchmarks collectively cover the threat surface: a 46 Target Technique matrix grounded in STRIDE…