arXiv subjects

Zhipeng Yan

Publications and source records attributed to Zhipeng Yan.

5 recordsLinked to original sources

arXiv2026

SCOPE: Structured Decomposition and Conditional Skill Orchestration for Complex Image Generation

While text-to-image models have made strong progress in visual fidelity, faithfully realizing complex visual intents remains challenging because many requirements must be tracked across grounding, generation, and verification. We refer to these requirements as semantic commitments and formalize their lifecycle discontinuity as the Conceptual Rift, where commitments may be locally resolved or checked but fail to remain identifiable as the same operational units throughout the generation lifecycle. To address this, we propose SCOPE, a specification-guided skill orchestration framework that maintains semantic commitments in an evolving structured specification and conditionally invokes retrieval, reasoning, and repair skills around unresolved or violated commitments. To evaluate commitment-level intent realization, we introduce Gen-Arena, a human-annotated benchmark with entity- and constraint-level specifications, together with Entity-Gated Intent Pass Rate (EGIP), a strict entity-first pass criterion. SCOPE substantially outperforms all evaluated baselines on Gen-Arena, achieving 0.60 EGIP, and further achieves strong results on WISE-V (0.907) and MindBench (0.61), demonstrating the effectiveness of persistent commitment tracking for complex image generation.

cs.CV↗

arXiv2025

Loud-loss: A Perceptually Motivated Loss Function for Speech Enhancement Based on Equal-Loudness Contours

The mean squared error (MSE) is a ubiquitous loss function for speech enhancement, but its problem is that the error cannot reflect the auditory perception quality. This is because MSE causes models to over-emphasize low-frequency components which has high energy, leading to the inadequate modeling of perceptually important high-frequency information. To overcome this limitation, we propose a perceptually-weighted loss function grounded in psychoacoustic principles. Specifically, it leverages equal-loudness contours to assign frequency-dependent weights to the reconstruction error, thereby penalizing deviations in a way aligning with human auditory sensitivity. The proposed loss is model-agnostic and flexible, demonstrating strong generality. Experiments on the VoiceBank+DEMAND dataset show that replacing MSE with our loss in a GTCRN model elevates the WB-PESQ score from 2.17 to 2.93-a significant improvement in perceptual quality.

cs.SD↗

arXiv2025

Two-stage Audio-Visual Target Speaker Extraction System for Real-Time Processing On Edge Device

Audio-Visual Target Speaker Extraction (AVTSE) aims to isolate a target speaker's voice in a multi-speaker environment with visual cues as auxiliary. Most of the existing AVTSE methods encode visual and audio features simultaneously, resulting in extremely high computational complexity and making it impractical for real-time processing on edge devices. To tackle this issue, we proposed a two-stage ultra-compact AVTSE system. Specifically, in the first stage, a compact network is employed for voice activity detection (VAD) using visual information. In the second stage, the VAD results are combined with audio inputs to isolate the target speaker's voice. Experiments show that the proposed system effectively suppresses background noise and interfering voices while spending little computational resources.

cs.SD↗

arXiv2018

Unsupervised Learning for Large-Scale Fiber Detection and Tracking in Microscopic Material Images

Constructing 3D structures from serial section data is a long standing problem in microscopy. The structure of a fiber reinforced composite material can be reconstructed using a tracking-by-detection model. Tracking-by-detection algorithms rely heavily on detection accuracy, especially the recall performance. The state-of-the-art fiber detection algorithms perform well under ideal conditions, but are not accurate where there are local degradations of image quality, due to contaminants on the material surface and/or defocus blur. Convolutional Neural Networks (CNN) could be used for this problem, but would require a large number of manual annotated fibers, which are not available. We propose an unsupervised learning method to accurately detect fibers on the large scale, that is robust against local degradations of image quality. The proposed method does not require manual annotations, but uses fiber shape/size priors and spatio-temporal consistency in tracking to simulate the supervision in the training of the CNN. Experiments show significant improvements over state-of-the-art fiber detection algorithms together with advanced tracking performance.

cs.CV↗

arXiv2016

Economical Energy Efficiency E3: An Advanced Performance Metric for 5G Systems

The performances of the fifth generation (5G) wireless communication systems are significantly affected by edge cache and transport network. These emerging components bring substantial costs of the placement and utilization, and the evaluation of the cost impact is beyond the capability of traditional performance metrics, including spectral efficiency (SE) and energy efficiency (EE). In this article, economical energy efficiency (E3) is proposed, whose core idea is to take SE/EE and cost into account to evaluate comprehensive gains when different kinds of advanced technologies are used in 5G systems. The E3results are shown when the transport network and edge cache are separately or jointly used. Open issues in terms of modeling the cost, E3optimization based radio resource allocation, and E3optimization for internet of things, are identified as well.

cs.IT↗