48 citations · 73 across the 11 of their papers we have counts for
4 papers · 1 filter
Is Better Teacher Supervision Enough? Unlocking Student-side Learning in Multimodal On-Policy Distillation
Siyuan Liu, Kanghui Tian, Yue Duan +4
On-policy distillation (OPD) improves reasoning by providing token-level supervision from a teacher on a student's own trajectories. Existing methods primarily focus on enhancing t…
One Token, Two Fates: A Unified Framework via Vision Token Manipulation Against MLLMs Hallucination
Zhan Fa, Yue Duan, Jian Zhang +2
Current training-free methods tackle MLLM hallucination with separate strategies: either enhancing visual signals or suppressing text inertia. However, these separate methods are i…
When Shared Knowledge Hurts: Spectral Over-Accumulation in Model Merging
Yayuan Li, Ze Peng, Jian Zhang +3
Model merging combines multiple fine-tuned models into a single model by adding their weight updates, providing a lightweight alternative to retraining. Existing methods primarily…
Decomposing and Composing: Towards Efficient Vision-Language Continual Learning via Rank-1 Expert Pool in a Single LoRA
Zhan Fa, Yue Duan, Jian Zhang +3
Continual learning (CL) in vision-language models (VLMs) faces significant challenges in improving task adaptation and avoiding catastrophic forgetting. Existing methods usually ha…