Alexey Shvets
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
NLP×2ML×2AI×1
Frequent co-authors
Research Timeline
2026
The Architecture of Errors: From Universal Impossibility to Patch-Local LLM Reliability
The paper reframes LLM reliability from an impossible universal problem to a manageable, local patch-based problem, showing that sufficient interventions can be found by focusing on recurring failure modes within bounded operational domains.
PALS: Percentile-Aware Layerwise Sparsity for LLM Pruning
The paper proposes PALS, a method for adjusting per-layer sparsity based on activation magnitudes in transformer models, achieving better performance than uniform one-shot pruning methods.
Highlighted terms show continued research focus across papers
Papers
cs.CLcs.LGEmpiricalRecentJul 8, 2026
PALS: Percentile-Aware Layerwise Sparsity for LLM Pruning
The paper proposes PALS, a method for adjusting per-layer sparsity based on activation magnitudes in transformer models, achieving better performance than uniform one-shot pruning methods.
View →
cs.CLcs.AIcs.LGRecent