Less is More: Selective Reflection for Compatible and Efficient Knowledge Distillation in Large Language Models (2025 · 4 citations)
White-box knowledge distillation (KD) for LLMs has mostly been improved by designing new divergence losses or by mixing ground-truth and student-generated responses.
Calibrated Progressive Distillation: Co-Designing Curriculum and Target Mixing for Knowledge Distillation of Large Language Models (2026)
The paper addresses white-box knowledge distillation (KD) of LLMs. In this setting, the teacher–student capacity gap causes mode averaging or collapse. Existing remedies are curriculum learning and blending teacher and student distributions into the target, but they are typically tuned separately. The authors argue…
Learning from Evolving Training Dynamics: An Entropy-Maximizing Data Curation Strategy for LLM Supervised Post-Training (2026)
Curriculum learning for supervised post-training of LLMs usually ranks examples once, using a single static difficulty score such as Perplexity.

Co-authors here

1 co-author with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 4 times (of the 149,439 papers whose bibliographies we read); 1 citing paper with a page here →.

Updated 2 November 2026