Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ren, Yiming, Yang, Yujiu, Wang, Junjie
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2603.26330
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Inhaltsangabe:
  • Supervised fine-tuning (SFT) on visual instruction data often improves perceptual capabilities in vision-language models (VLMs) while degrading reasoning performance, creating a persistent reasoning tax during post-training. We investigate whether this degradation is related to disrupted access to depth-wise representations, and find that even fixed cross-depth aggregation substantially restores reasoning, suggesting that preserved cross-depth access is an important missing factor in VLM fine-tuning. Building on this observation, we propose Input-Adaptive Depth Aggregation (IADA), a lightweight mechanism that makes cross-depth retrieval input-adaptive, modality-aware, and efficiently parameterized through a low-rank bottleneck. On Qwen3-VL-2B, IADA improves the average reasoning score by 9.5 points and the average perception score by $3.3$ points over LoRA-only fine-tuning with only 0.14M additional parameters, with the strongest gains appearing in parameter-efficient low-rank settings.