PPL
Hongbo Wang
Papers (4)
Coloring the Noise: Adversarial Sobolev Alignment for Faithful Image Super ResolutionHarder to Defend: Towards Chinese Toxicity Attacks via Implicit Enhancement and Obfuscation RewritingBoostAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward ModelsPatRe: A Full-Stage Office Action and Rebuttal Generation Benchmark for Patent Examination