The paper investigates how teacher signals influence parameter updates in Multi‑Teacher On‑Policy Distillation (MOPD) by analyzing Qwen3‑1.7B and SmolLM3‑3B. It shows that loss averaging, Adam’s first‑moment bias, BF16 rounding, and the choice of averaging rule all shape the gradients and ultimately affect task performance. The study quantifies these effects, revealing, for example, that token‑averaging favors longer responses and that BF16 rounding masks most weight changes.
By Siqi Zhu, Suozhi Huang, Kaixuan Zhang, Yuheng Yang, Zhanyang Jin, Yihang Sun, Jiaxuan You
arXiv:2610.19876v1 Announce Type: new
Abstract: Continual learning aims to acquire new knowledge while retaining previously learned knowledge. However, updating shared parameters when learning new ta...
By Teif Aldaajani, Huda Hakami, Maha A. Thafar
The paper introduces TALON, a Task‑Adaptive LoRA‑Teacher framework for Few‑Shot Class‑Incremental Learning. TALON assigns a dedicated LoRA‑Teacher to each incremental task, then distills the frozen teachers into a single LoRA‑Student via Ensemble Knowledge Transfer, using a semantic‑guided weighting scheme to reduce forgetting and overfitting. Experiments on four FSCIL benchmarks show that TALON matches or surpasses state‑of‑the‑art accuracy while using up to 33× fewer deployment parameters and cutting inference time by 41.7%.
By Hongwei Zhao (School of Computer Science,Engineering, Beihang University), Rui Liu (School of Computer Science,Engineering, Beihang University), Yansong Liu (School of Computer Science,Engineering, Beihang University), Zhiyuan Zou (School of Computer Science,Engineering, Beihang University), Yong Chen (School of Computer Science, Beijing University of Posts,Telecommunications)
arXiv:2606. 12171v1 Announce Type: cross Abstract: Knowledge Distillation (KD) and mixup have proven effective at inducing smoothness in class boundaries; KD captures inherent class relationships in probability distributions, and mixup enforces them through convex combinations of inputs.
By Jos\'e Medina, Paul Honeine, Abdelaziz Bensrhair, Amnir Hadachi
arXiv:2609.36734v1 Announce Type: new
Abstract: Knowledge Distillation (KD) trains a smaller-capacity student model to imitate a larger-capacity teacher model by matching output distributions, implic...
By Ayan Sengupta, Vaibhav Seth, Tanmoy Chakraborty
arXiv:2609.37702v1 Announce Type: cross
Abstract: Class Incremental Learning (Class-IL) requires models to learn new classes over time while preserving previously acquired knowledge without access to...
By A. L. S. Conde, Y. Elkhatib, C. M. Ranieri
Accuracy degradation is the standard metric for Catastrophic Forgetting (CF), however, it records only whether forgetting occurred or not. It saturates at the extremes and collapses discretely at task boundaries, hiding the internal structure of what is being forgotten.
arXiv:2606. 25165v1 Announce Type: new Abstract: Accuracy degradation is the standard metric for Catastrophic Forgetting (CF), however, it records only whether forgetting occurred or not.
By Ahmed Anwar, Andreas Wagner, Federico Raue, Tobias Nauen, Andreas Dengel
arXiv:2608. 14634v1 Announce Type: new Abstract: Biological intelligence naturally prevents catastrophic forgetting through Complementary Learning Systems (CLS) theory, a macroscopic consolidation process driven at the local level by synaptic metaplasticity: the continuous, history-dependent neuromodulation of individual synapses.
By Isabelle Aguilar, Zayn Andre Zainal, Omid Kavehei
arXiv:2604. 10688v2 Announce Type: replace-cross Abstract: On-policy reinforcement learning has become the dominant paradigm for reasoning alignment in large language models, yet its sparse, outcome-level rewards make token-level credit assignment notoriously difficult.
By Binbin Zheng, Xing Ma, Yiheng Liang, Jingqing Ruan, Xiaoliang Fu, Kepeng Lin, Benchang Zhu, Ke Zeng, Xunliang Cai
The paper investigates how the sampled-token reverse-KL loss in on‑policy distillation distributes updates across tokens. By analyzing the gradient of the per‑token K2 estimator, the authors find that tokens with low student probability and large teacher‑student gaps receive disproportionately large gradient norms. They propose Surprise‑aware Reweighting (SuRe), a lightweight weighting rule that further amplifies this allocation, and demonstrate that SuRe improves math metrics on Qwen3 student models without harming out‑of‑domain performance.
By Bing Shao, Jiazheng Zhang, Long Ma, Yujiong Shen, Senjie Jin, Xin Guo, Yuming Yang, Mingxu Chai, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang
arXiv:2605. 12765v3 Announce Type: replace Abstract: Large Language Models memorize vast amounts of training data, raising concerns regarding privacy, copyright infringement, and safety.
By Vin\'icius Conte Turani, Ot\'avio Parraga, Jo\~ao Vitor Boer Abitante, Kristen K. Arguello, Joana Pasquali, Ramiro N. Barros, Flavio du Pin Calmon, Christian Mattjie, Rodrigo C. Barros, Lucas S. Kupssinsk\"u