Searcharxiv⌕ Search

arXiv subjects

Junzhi Yang

Publications and source records attributed to Junzhi Yang.

2 recordsLinked to original sources

Where Do Vision-Language Models Get Left and Right? Position-Code Counterfactuals in Qwen2.5-VL, Qwen3-VL and InternVL3

A vision-language model may take left-right direction from the orientation of image content within patches, its vision transformer's (ViT) position code, or token positions and order in its language model (LLM). Ablations show the ViT code is necessary; we test sufficiency by mirroring only a position code. In Qwen2.5-VL-7B, Qwen3-VL-4B and InternVL3-2B, mirroring ViT width positions reproduces the flipped-image answer on 84.3-93.2% of CV-Bench left-right questions (Qwen2.5-VL-3B: 87.5%, partly a left fallback). With two options, this also counts disruption; a half-grid shift flips most answers too. With the ViT code intact, LLM-side id and token-order mirrors change few left-right answers in all three series (a weak id test in Qwen2.5-VL). In Qwen2.5-VL-7B the effect sits in the global-attention ViT blocks, mostly the last. On What'sUp, flipping content and token order, not the position code, keeps more on/under than left-right answers at the flipped-image answer. Post hoc analyses qualify these results. On CV-Bench items with located objects, random permutations flip 18.9-31.0 points more answers when reversing the objects' order than when keeping it. On What'sUp, in Qwen2.5-VL and Qwen3-VL, the share of the left-right changes made by random permutations that land on the mirror relation is mostly below chance. Counted as returns to the original answer, the What'sUp contrast of support with left-right relations is clear only in InternVL3-2B. Most remaining errors give the same relation whichever object is asked about, suggesting that repair may target relation binding, object localization or use of the reference object.

cs.CV↗

A sol-gel method for growing superconducting MgB2 films

In this paper we report a new sol-gel method for the fabrication of MgB2 films. Polycrystalline MgB2 films were prepared by spin-coating a precursor solution of Mg(BH_4)_2 diethyl ether on (001)Al2O3 substrates followed with annealing in Mg vapor. In comparison with the MgB2 films grown by other techniques, our films show medium qualities including a superconducting transition temperature of Tc ~ 37 K, a critical current density of Jc(5 K, 0 T) ~ 5 {\times} 10^6 A cm^{-2}, and a critical field of H_{c2}(0) ~ 19 T. Such a sol-gel technique shows potential in the commercial fabrication of practically used MgB2 films as well as MgB2 wires and tapes.

cond-mat.supr-con↗