DART: Distillation-Aware Reparameterization for Training-Free LoRA Reuse in Few-

arXiv:2610.14693v1 Announce Type: new Abstract: Explicit point correspondence is attractive for adapting video generators: it describes how visible surfaces move, but can

arXiv:2604.27796v1 Announce Type: new Abstract: Exponential growth in the scale of modern foundation models has led to the widespread adoption of Low-Rank Adaptation (LoRA) as a

arXiv:2605.11458v1 Announce Type: new Abstract: On-policy self-distillation has become a strong recipe for LLM reasoning, where a privileged teacher supervises the student's own

arXiv:2603.22324v1 Announce Type: cross Abstract: We introduce Delta-Aware Quantization (DAQ), a data-free post-training quantization framework that preserves the knowledge

arXiv:2605.04341v1 Announce Type: cross Abstract: We study distillation for large language models under explicit compute constraints, with the goal of producing student models

arXiv:2604.00421v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) layers increase model capacity by activating only a small subset of experts per token, and typically rely

arXiv:2605.00422v1 Announce Type: cross Abstract: Large language models (LLMs) have driven major progress in NLP, yet their substantial memory and compute demands still hinder

arXiv:2610.02678v1 Announce Type: new Abstract: On-policy distillation (OPD) combines student-generated rollouts with dense token-level supervision from a teacher, but providing