Yong Yang

The paper proposes IntraGuard, a black-box, venue-agnostic defense framework that embeds hidden instructions into manuscripts via PDF structure to disrupt AI-generated peer reviews, achieving up to 84% defense success.

ADWIN introduces an adaptive window framework for on-policy distillation (OPD) that efficiently manages the supervision horizon by training on short, teacher-anchored prefixes while using delayed full-rollout probes to maintain alignment, significantly reducing training cost while preserving accuracy.

The paper introduces Logit-aware Final-block Quantization (LFQ), an enhancement to block-wise quantization that quantizes the final Transformer block using a cross-entropy loss to significantly boost the generation quality of low-bit quantized LLMs.

The paper proposes an Understanding-Enhanced Model Collaboration Method (UE-MCM) to accurately detect subtle and rare mistakes in egocentric videos by combining coarse-grained workflow understanding with fine-grained action reasoning.