3 papers
cs.CV2026
Conditional Visual Evidence Utility: State-Dependent Rank Reversals in Frozen Vision-Language Encoders
Yunxuan Fang, Xinhe Wang
Static importance scores compress visual evidence into a single ranking, but the value of remaining evidence can change after one cue has been observed. We study this possibility i…
cs.LG2026
When Adaptation Fails: A Gradient-Based Diagnosis of Collapsed Gating in Vision-Language Prompt Learning
Yunxuan Fang, Ziwei Zhang, Xinhe Wang
Adaptive prompting mechanisms have been proposed to enhance vision-language models by dynamically tailoring prompts to inputs. However, in frozen few-shot prompt learning with CLIP…
cs.LG2026
A Controlled Diagnostic Study of Hardware-Induced Distortions in Hardware-Aware Training
Yunxuan Fang, Xinhe Wang
Hardware-aware training (HAT) is widely used to improve the robustness of neural networks on non-ideal AI accelerators, such as analog in-memory computing (IMC) systems. However, n…