pith. sign in

Rongsheng Li

Identifiers

  • name variant Rongsheng Li 0.60 · backfill

Papers (2)

  1. Repurposing Adversarial Perturbations for Continual Learning: From Defense to Active Alignment cs.LG · 2026 · author #6
  2. The Granularity Mismatch in Agent Security: Argument-Level Provenance Solves Enforcement and Isolates the LLM Reasoning Bottleneck cs.CR · 2026 · author #5

Mentions

  • 2606.02322 #6 · arxiv_oai · confidence 0.70 Rongsheng Li

Frequent Coauthors