arXiv subjects

Zhiyuan Yin

Publications and source records attributed to Zhiyuan Yin.

6 recordsLinked to original sources

arXiv2025

Codebook-Centric Deep Hashing: End-to-End Joint Learning of Semantic Hash Centers and Neural Hash Function

Hash center-based deep hashing methods improve upon pairwise or triplet-based approaches by assigning fixed hash centers to each class as learning targets, thereby avoiding the inefficiency of local similarity optimization. However, random center initialization often disregards inter-class semantic relationships. While existing two-stage methods mitigate this by first refining hash centers with semantics and then training the hash function, they introduce additional complexity, computational overhead, and suboptimal performance due to stage-wise discrepancies. To address these limitations, we propose $\textbf{Center-Reassigned Hashing (CRH)}$, an end-to-end framework that $\textbf{dynamically reassigns hash centers}$ from a preset codebook while jointly optimizing the hash function. Unlike previous methods, CRH adapts hash centers to the data distribution $\textbf{without explicit center optimization phases}$, enabling seamless integration of semantic relationships into the learning process. Furthermore, $\textbf{a multi-head mechanism}$ enhances the representational capacity of hash centers, capturing richer semantic structures. Extensive experiments on three benchmarks demonstrate that CRH learns semantically meaningful hash centers and outperforms state-of-the-art deep hashing methods in retrieval tasks.

cs.CV↗

arXiv2025

INFELM: In-depth Fairness Evaluation of Large Text-To-Image Models

The rapid development of large language models (LLMs) and large vision models (LVMs) have propelled the evolution of multi-modal AI systems, which have demonstrated the remarkable potential for industrial applications by emulating human-like cognition. However, they also pose significant ethical challenges, including amplifying harmful content and reinforcing societal biases. For instance, biases in some industrial image generation models highlighted the urgent need for robust fairness assessments. Most existing evaluation frameworks focus on the comprehensiveness of various aspects of the models, but they exhibit critical limitations, including insufficient attention to content generation alignment and social bias-sensitive domains. More importantly, their reliance on pixel-detection techniques is prone to inaccuracies. To address these issues, this paper presents INFELM, an in-depth fairness evaluation on widely-used text-to-image models. Our key contributions are: (1) an advanced skintone classifier incorporating facial topology and refined skin pixel representation to enhance classification precision by at least 16.04%, (2) a bias-sensitive content alignment measurement for understanding societal impacts, (3) a generalizable representation bias evaluation for diverse demographic groups, and (4) extensive experiments analyzing large-scale text-to-image model outputs across six social-bias-sensitive domains. We find that existing models in the study generally do not meet the empirical fairness criteria, and representation bias is generally more pronounced than alignment errors. INFELM establishes a robust benchmark for fairness assessment, supporting the development of multi-modal AI systems that align with ethical and human-centric principles.

cs.CV↗

arXiv2024

An Economical and Efficient Helium Recovery System for Vibration-Sensitive Applications

We present the design of a helium liquefaction system tailored to efficiently recover helium vapor from either an individual or a small cluster of vibration-sensitive cryogenic instruments. This design prioritizes a compact footprint, mitigating potential contamination sources such as gas bags and oil-lubricated compressors while maximizing the recovery rate by capturing both the boil-offs during normal operation and refilling process of the bath cryostat. We demonstrated its performance by applying it to a commercial low-temperature scanning probe microscope. It features a > 94% recovery rate and induces negligible vibrational noise to the microscope. Due to its adaptability, affordability, compact size, and suitability for homemade setups, we foresee that our design can be utilized across a wide range of experimental measurements where liquid helium is used as the cryogen.

cond-mat.mes-hall↗

arXiv2024

Operating a Multi-Level Molecular Dimer Switch through Precise Tip-Molecule Control

Controlling structural transitions between molecular configurations is crucial for advancing functional molecular electronics. While reversible switching of bistable two-state molecules has been achieved, creating molecular systems that can be controllably switched between multiple configurations often requires complex synthetic methods, presenting a much greater challenge. In this study, we showcase a straightforward yet effective strategy to create and control transitions between multiple molecular structural states by forming a surface-bound molecular dimer. Using low-temperature scanning tunneling microscopy, we induce and characterize the structural transitions of a pyrrolidine dimer on a Cu(100) surface. The intermolecular interactions open new energy transfer channels, enabling the excitation through pathways that were inaccessible in monomers. The occupation of different molecular states is highly sensitive to both the energy of the tunneling electrons and the interaction with the STM tip. By precisely adjusting the tip-molecule distance, we can select the most probable structural configuration based on sample bias, thereby achieving on-demand control of this molecular dimer switch. This work highlights an approach that leverages both intermolecular and molecule-environment interactions to create and control an artificially fabricated molecular device.

physics.chem-ph↗

arXiv2024

Nano-Scale Manipulation of Single-Molecule Conformational Transition Through Vibrational Excitation

On-demand control of molecular actions is essential for realizing single-molecule functional devices. Such a control can be achieved by manipulating interactions between individual molecules and their nanoscale environment. In this study, we manipulate the conformational transition of a single pyrrolidine molecule on a Cu(100) surface by exciting its vibra-tions with tunneling electrons using scanning tunneling microscopy. Multiple transition pathways between two structural states are identified to be driven by distinct vibrational modes, whose corresponding nuclear motions are determined by density functional theory calculations. Tip-induced van der Waals forces and intermolecular interactions enable precise tuning of molecule-environment interactions, allowing modulation of vibrational energies, alteration of transition probabilities, and selection of the lowest energy transition pathway. This work reveals how external force fields in a tunable nanocavity can modulate molecular conformational transitions, offering an approach to deliberately engineer molecule-environment interactions for specific molecular functions.

physics.chem-ph↗

arXiv2013

Almost Optimal Channel Access in Multi-Hop Networks With Unknown Channel Variables

We consider distributed channel access in multi-hop cognitive radio networks. Previous works on opportunistic channel access using multi-armed bandits (MAB) mainly focus on single-hop networks that assume complete conflicts among all secondary users. In the multi-hop multi-channel network settings studied here, there is more general competition among different communication pairs. We formulate the problem as a linearly combinatorial MAB problem that involves a maximum weighted independent set (MWIS) problem with unknown weights which need to learn. Existing methods for MAB where each of $N$ nodes chooses from $M$ channels have exponential time and space complexity $O(M^N)$, and poor theoretical guarantee on throughput performance. We propose a distributed channel access algorithm that can achieve $1/ρ$ of the optimum averaged throughput where each node has communication complexity $O(r^2+D)$ and space complexity $O(m)$ in the learning process, and time complexity $O(D m^{ρ^r})$ in strategy decision process for an arbitrary wireless network. Here $ρ=1+ε$ is the approximation ratio to MWIS for a local $r$-hop network with $m<N$ nodes,and $D$ is the number of mini-rounds inside each round of strategy decision. For randomly located networks with an average degree $d$, the time complexity is $O(d^{ρ^r})$.

cs.NI↗