arXiv subjects

Mengyu Gao

Publications and source records attributed to Mengyu Gao.

6 recordsLinked to original sources

arXiv2026

Causality-guided Prompt Learning for Vision-language Models via Visual Granulation

Prompt learning has recently attracted much attention for adapting pre-trained vision-language models (e.g., CLIP) to downstream recognition tasks. However, most of the existing CLIP-based prompt learning methods only show a limited ability for handling fine-grained datasets. To address this issue, we propose a causality-guided text prompt learning method via visual granulation for CLIP, called CaPL, where the explored visual granulation technique could construct sets of visual granules for the text prompt to capture subtle discrepancies among different fine-grained classes through casual inference. The CaPL method contains the following two modules: (1) An attribute disentanglement module is proposed to decompose visual features into non-individualized attributes (shared by some classes) and individualized attributes (specific to single classes) using a Brownian Bridge Diffusion Model; (2) A granule learning module is proposed to construct visual granules by integrating the aforementioned attributes for recognition under two causal inference strategies. Thanks to the learned visual granules, more discriminative text prompt is expected to be learned. Extensive experimental results on 15 datasets demonstrate that our CaPL method significantly outperforms the state-of-the-art prompt learning methods, especially on fine-grained datasets.

cs.CV↗

arXiv2025

Complementary Frequency-Varying Awareness Network for Open-Set Fine-Grained Image Recognition

Open-set image recognition is a challenging topic in computer vision. Most of the existing works in literature focus on learning more discriminative features from the input images, however, they are usually insensitive to the high- or low-frequency components in features, resulting in a decreasing performance on fine-grained image recognition. To address this problem, we propose a Complementary Frequency-varying Awareness Network that could better capture both high-frequency and low-frequency information, called CFAN. The proposed CFAN consists of three sequential modules: (i) a feature extraction module is introduced for learning preliminary features from the input images; (ii) a frequency-varying filtering module is designed to separate out both high- and low-frequency components from the preliminary features in the frequency domain via a frequency-adjustable filter; (iii) a complementary temporal aggregation module is designed for aggregating the high- and low-frequency components via two Long Short-Term Memory networks into discriminative features. Based on CFAN, we further propose an open-set fine-grained image recognition method, called CFAN-OSFGR, which learns image features via CFAN and classifies them via a linear classifier. Experimental results on 3 fine-grained datasets and 2 coarse-grained datasets demonstrate that CFAN-OSFGR performs significantly better than 9 state-of-the-art methods in most cases.

cs.CV↗

arXiv2025

Bright hybrid excitons in molecularly tunable bilayer crystals

Bilayer crystals, built by stacking crystalline monolayers, generate interlayer potentials that govern excitonic phenomena but are constrained by fixed covalent lattices and orientations. Replacing one layer with an atomically thin molecular crystal overcomes this limitation, as diverse functional groups enable tunable molecular lattices and interlayer potentials, tailoring a wide range of excitonic properties. Here, we report hybrid excitons in four-atom-thick hybrid bilayer crystals (HBCs), directly synthesized with single-crystalline perylene diimide (PDI) molecular crystal atop WS2 monolayers. These excitons arise from a hybridized bilayer band structure, revealed by lattice-scale first-principles calculations, inheriting properties from both monolayers. They exhibit bright photoluminescence with near-unity polarization above and below the WS2 bandgap, along with spectral signatures of exciton delocalization, supported by theory, while their energies and intensities are tuned by modifying the HBC composition by synthesis. Our work introduces a molecule-based 2D quantum materials platform for bottom-up design and control of optoelectronic properties.

cond-mat.mtrl-sci↗

arXiv2025

Molecular tuning of excitons in four-atom-thick hybrid bilayer crystals

Bilayer crystals, formed by stacking monolayers of two-dimensional (2D) crystals, create interlayer potentials that govern excitonic phenomena but are constrained by their fixed covalent lattices. Replacing one layer with an atomically thin molecular crystal overcomes this limitation, as precise control of functional groups enables tunable 2D molecular lattices and, consequently, electronic structures. Here, we report molecular tuning of lattices and excitons in four-atom-thick hybrid bilayer crystals (HBCs), synthesized as monolayers of perylene-based molecular and transition metal dichalcogenide (TMD) single crystals. In HBCs, we observe an anisotropic photoluminescence signal exhibiting characteristics of both molecular and TMD excitons, directly tuned by molecular geometry and HBC composition. Ab initio calculations reveal that this anisotropic emission arises from hybrid excitons, which inherit properties from both layers through a hybridized bilayer band structure. Our work establishes a synthetically derived, molecule-based 2D quantum materials platform with the potential for engineering interlayer potentials.

cond-mat.mtrl-sci↗

arXiv2021

Vibrational relaxation dynamics in layered perovskite quantum wells

Organic-inorganic layered perovskites are two-dimensional quantum wells with layers of lead-halide octahedra stacked between organic ligand barriers. The combination of their dielectric confinement and ionic sublattice results in excitonic excitations with substantial binding energies that are strongly coupled to the surrounding soft, polar lattice. However, the ligand environment in layered perovskites can significantly alter their optical properties due to the complex dynamic disorder of soft perovskite lattice. Here, we observe the dynamic disorder through phonon dephasing lifetimes initiated by ultrafast photoexcitation employing high-resolution resonant impulsive stimulated Raman spectroscopy of a variety of ligand substitutions. We demonstrate that vibrational relaxation in layered perovskite formed from flexible alkyl-amines as organic barriers is fast and relatively independent of the lattice temperature. Relaxation in aromatic amine based layered perovskite is slower, though still fast relative to pure inorganic lead bromide lattices, with a rate that is temperature dependent. Using molecular dynamics simulations, we explain the fast rates of relaxation by quantifying the large anharmonic coupling of the optical modes with the ligand layers and rationalize the temperature independence due to their amorphous packing. This work provides a molecular and time-domain depiction of the relaxation of nascent optical excitations and opens opportunities to understand how they couple to the complex layered perovskite lattice, elucidating design principles for optoelectronic devices.

cond-mat.mtrl-sci↗

arXiv2020

Solid-state ionic rectification in perovskite nanowire heterostructures

Halide perovskites have attracted increasing research attention regarding their outstanding optoelectronic applications. Owing to its low activation energy, ion migration is implicated in the long-term stability and many unusual transport behaviors of halide perovskite devices. However, precise control of the ionic transport in halide perovskite crystals remains challenging. Here we visualized and quantified the electric-field-induced halide ion migration in an axial CsPbBr$_3$-CsPbCl$_3$ nanowire heterostructure and demonstrated a solid-state ionic rectification, which is due to the non-uniform distribution of the ionic vacancies in the nanowire that results from a competition between electrical screening and their creation and destruction at the electrode interface. The asymmetric heterostructure characteristics add an additional knob to the ion-movement manipulation in the design of advanced ionic circuits with halide perovskites as building blocks.

physics.app-ph↗