Zilong Liu

Zilong Liu, Xuewen Zhang, Jinrui Xing et al.

Knowledge distillation (KD) is a key technique for compressing Large Language Models (LLMs), yet methods relying on a single KL objective often fail to balance primary distribution fitting with long-tail probability modeling, limiting both generation quality and generalization. To address this, we analyze the complementary roles of forward and reverse KL divergence (FKL/RKL) in distribution alignment from theoretical and empirical perspectives. We then propose a reinforcement-learning-based adaptive KL-weighted distillation framework, in which a policy network dynamically assigns weights to FKL and RKL based on teacher-student distributional characteristics, guided by immediate reward signals to achieve dual alignment on principal and long-tail modes. Extensive experiments demonstrate consistent improvements across Rouge-L and BertScore metrics, surpassing greedy heuristics by 0.4-0.6 points and outperforming other baseline methods on diverse benchmarks.

Zi-Long Liu, Chi-Man Pun

Reversible data hiding in encrypted image (RDHEI) becomes a hot topic, and a lot of algorithms have been proposed to optimize this technology. However, these algorithms cannot achieve strong embedding capacity. Thus, in this paper, we propose an advanced RDHEI scheme based on lossless pixel conversion (LPC). Different from the previous RDHEI algorithms, LPC is inspired by the planar map coloring question, and it performs a dynamic image division process to divide the original image into irregular regions instead of regular blocks as in the previous RDHEI algorithms. In the process of LPC, pixel conversion is performed by region; that is, pixels in the same regions are converted to the same conversion values, which will occupy a smaller size, and then the available room can be reserved to accommodate additional data. LPC is a reversible process, so the original image can be losslessly recovered on the receiver side. Experimental results show that the embedding capacity of the proposed scheme outperforms the existing RDHEI algorithms.