arXiv subjects

Xiaowei Liang

Publications and source records attributed to Xiaowei Liang.

5 recordsLinked to original sources

arXiv2026

Global-Local Dual Perception for MLLMs in High-Resolution Text-Rich Image Translation

Text Image Machine Translation (TIMT) aims to translate text embedded in images in the source-language into target-language, requiring synergistic integration of visual perception and linguistic understanding. Existing TIMT methods, whether cascaded pipelines or end-to-end multimodal large language models (MLLMs),struggle with high-resolution text-rich images due to cluttered layouts, diverse fonts, and non-textual distractions, resulting in text omission, semantic drift, and contextual inconsistency. To address these challenges, we propose GLoTran, a global-local dual visual perception framework for MLLM-based TIMT. GLoTran integrates a low-resolution global image with multi-scale region-level text image slices under an instruction-guided alignment strategy, conditioning MLLMs to maintain scene-level contextual consistency while faithfully capturing fine-grained textual details. Moreover, to realize this dual-perception paradigm, we construct GLoD, a large-scale text-rich TIMT dataset comprising 510K high-resolution global-local image-text pairs covering diverse real-world scenarios. Extensive experiments demonstrate that GLoTran substantially improves translation completeness and accuracy over state-of-the-art MLLMs, offering a new paradigm for fine-grained TIMT under high-resolution and text-rich conditions.

cs.CV↗

arXiv2024

Augmented LRFS-based Filter: Holistic Tracking of Group Objects

This paper addresses the problem of group target tracking (GTT), wherein multiple closely spaced targets within a group pose a coordinated motion. To improve the tracking performance, the labeled random finite sets (LRFSs) theory is adopted, and this paper develops a new kind of LRFSs, i.e., augmented LRFSs, which introduces group information into the definition of LRFSs. Specifically, for each element in an LRFS, the kinetic states, track label, and the corresponding group information of its represented target are incorporated. Furthermore, by means of the labeled multi-Bernoulli (LMB) filter with the proposed augmented LRFSs, the group structure is iteratively propagated and updated during the tracking process, which achieves the simultaneously estimation of the kinetic states, track label, and the corresponding group information of multiple group targets, and further improves the GTT tracking performance. Finally, simulation experiments are provided, which well demonstrates the effectiveness of the labeled multi-Bernoulli filter with the proposed augmented LRFSs for GTT tracking.

eess.SY↗

arXiv2021

Spin-flip-driven giant magneto-transport in A-type antiferromagnet NaCrTe2

For anisotropic magneto-resistance (AMR) effect, its value synergistically depends on the magnitudes of magneto-resistance (MR) and magneto-crystalline anisotropy energy (MAE) simultaneously. In a magnetic material, the concurrence of gigantic AMR and MR signals is rather difficult due to weak spin-lattice coupling and small MAE. Here we report the considerable magneto-transport effect in layered A-type antiferromagnetic (AFM) NaCrTe2 by realigning the spin configurations. By applying H, the antiparallel spins of adjacent layers are flipped to ferromagnetic (FM) coupling either Ising-type along c-axis or XY-type within ab-plane. Theoretical calculations reveal that the energy bandgap narrows from 0.39 eV to 0.11 eV, accompanying a transition from semiconductor (high-R state) and half-semiconductor (low-R state), respectively. Thus, gigantic negative MR ratio of -90% is obtained at 10 K. More importantly, the decrement of R along H//c is far quicker than that of H//ab because the MAE of Ising-FM state is 1017 μeV/Cr3+ lower than that of XY-FM. The distinct trends result in the AMR ratio of 732% at 10 K, which is the record value to our best knowledge. These findings unravel the intrinsic origin of magneto in NaCrTe2 and will stimulate us to exploring the H-sensitive transport property in more AFM materials.

cond-mat.mtrl-sci↗

arXiv2021

Prediction of high-Tc superconductivity in ternary lanthanum borohydrides

The study of superconductivity in compressed hydrides is of great interest due to measurements of high critical temperatures (Tc) in the vicinity of room temperature, beginning with the observations of LaH10 at 170-190 GPa. However, the pressures required for synthesis of these high Tc superconducting hydrides currently remain extremely high. Here we show the investigation of crystal structures and superconductivity in the La-B-H system under pressure with particle-swarm intelligence structure searches methods in combination with first-principles calculations. Structures with six stoichiometries, LaBH, LaBH3, LaBH4, LaBH6, LaBH7 and LaBH8, were predicted to become stable under pressure. Remarkably, the hydrogen atoms in LaBH8 were found to bond with B atoms in a manner that is similar to that in H3S. Lattice dynamics calculations indicate that LaBH7 and LaBH8 become dynamically stable at pressures as low as 109.2 and 48.3 GPa, respectively. Moreover, the two phases were predicted to be superconducting with a critical temperature (Tc) of 93 K and 156 K at 110 GPa and 55 GPa, respectively. Our results provide guidance for future experiments targeting new hydride superconductors with both low synthesis pressures and high Tc.

cond-mat.mtrl-sci↗

arXiv2019

Superconductivity in Li-intercalated 1T-SnSe2 driven by electric-field gating

Creating carrier reservoirs in layered compounds can effectively tune the carrier density, which often induces a variety of emergent properties. Based on solid-ion-conductor gating technique, we successfully induce superconductivity of 4.8 K in ultrathin Li-intercalated SnSe2 samples. The Li+ ions are driven in between interspacing of SnSe2 layers and form a single reservoir layer to provide electrons. In addition, a dome-like T c is found through substituting of S for Se, where the optimal T c is 6.2 K for SnSe1.8S0.2. Density functional theory calculations confirm that the intercalated LiSnSe2 is thermodynamically favorable, where the intercalation of Li expands the interlayer spacing by 10% and increases the carrier density by two orders of magnitude. Meanwhile the calculated results reveal that the enhanced electron-phonon interaction due to softened phonon determines the occurrence of superconductivity. Our results demonstrate that this strategy is very effective to explore superconductors in layered materials with narrow bandgap.

cond-mat.supr-con↗