arXiv subjects

Pengcheng Yuan

Publications and source records attributed to Pengcheng Yuan.

8 recordsLinked to original sources

arXiv2026

SIRF: A Spec-Internalized Risk Foundation Model for Industrial Content Risk Control

For industrial content risk control, the real deployment constraint is not average accuracy but how much risk can be auto-handled under high precision and second-level latency. We present SIRF (Spec-Internalized Risk Foundation Model), which internalizes a platform's complex policies, synthesized without additional human annotation via EntiGraph, MAGA rewriting and account-level chain-of-thought (CoT), into the weights via continued pretraining (CPT), so rules are applied at high precision under an ultra-low-latency, verdict-only deployment. A controlled same-source comparison (Qwen3-8B-SFT vs. SIRF-8B-SFT, identical policy injection and verdict-only output form, differing only in policy-grounded CPT) attributes the gain to internalization: SIRF-8B-SFT reaches 71.3% Black Recall@P95, +15.1pp over the baseline, using only ~70M CPT tokens without harming general ability, and among included, logprob-available models under this interface it matches or exceeds far larger systems. SIRF is deployed as a tree-model adjudication layer (20% more mis-penalized samples recovered) and transfers to a freezing scenario at low cost (~70% relative mis-penalization reduction).

cs.AI↗

arXiv2026

A Unified Per-Token Gating Family for On-Policy Distillation: FKL/RKL Mixing with Multi-Channel and Bias Coefficients

Per-token gating of forward/reverse KL losses has become a standard technique for on-policy knowledge distillation (OPD), but existing methods such as EOPD (Jin et al., 2026) and ToDi (Jung et al., 2025) each fix a single gating signal and a single gating direction, and the two have never been compared directly. We introduce a four-coefficient parameterization lambda_t = sigma(a * h_t + b * u(x) + c + d * gap_t) in which direction-aligned proxies of EOPD and ToDi appear as one-dimensional (1D) restrictions, and which adds multi-channel composition and an explicit bias as further degrees of freedom. On TweetEval (Barbieri et al., 2020) emotion and hate, with a Qwen3-32B teacher and a Qwen3-4B student, configurations in the full family reach higher accuracy than the matched-magnitude single-channel (entropy-only / gap-only) 1D restrictions in 33 of 36 comparable cells, and a 26-cell mean-match isolation experiment places dynamic gating ahead of effective-KL-matched static baselines in 19 of 26 cells. Because cells share training data, models, and parameter substructure, we report both counts as exploratory aggregate directional evidence rather than as independent hypothesis tests. Targeted three-seed paired replications of the nine headline comparisons singled out by that sweep -- including a third task, offensive -- are directionally consistent, but individually smaller than the single-seed estimates and not significant at n=3. We therefore present the parameterization primarily as a shared coordinate system for comparing per-token gating designs in short-output classification OPD.

cs.AI↗

arXiv2025

TflosYOLO+TFSC: An Accurate and Robust Model for Estimating Flower Count and Flowering Period

Tea flowers play a crucial role in taxonomic research and hybrid breeding for the tea plant. As traditional methods of observing tea flower traits are labor-intensive and inaccurate, we propose TflosYOLO and TFSC model for tea flowering quantifying, which enable estimation of flower count and flowering period. In this study, a highly representative and diverse dataset was constructed by collecting flower images from 29 tea accessions in 2 years. Based on this dataset, the TflosYOLO model was built on the YOLOv5 architecture and enhanced with the Squeeze-and-Excitation (SE) network, which is the first model to offer a viable solution for detecting and counting tea flowers. The TflosYOLO model achieved an mAP50 of 0.874, outperforming YOLOv5, YOLOv7 and YOLOv8. Furthermore, TflosYOLO model was tested on 34 datasets encompassing 26 tea accessions, five flowering stages, various lighting conditions, and pruned / unpruned plants, demonstrating high generalization and robustness. The correlation coefficient (R^2) between the predicted and actual flower counts was 0.974. Additionally, the TFSC (Tea Flowering Stage Classification) model, a 7-layer neural network was designed for automatic classification of the flowering period. TFSC model was evaluated on 2 years and achieved an accuracy of 0.738 and 0.899 respectively. Using the TflosYOLO+TFSC model, we monitored the tea flowering dynamics and tracked the changes in flowering stages across various tea accessions. The framework provides crucial support for tea plant breeding programs and phenotypic analysis of germplasm resources.

cs.CV↗

arXiv2024

RSBuilding: Towards General Remote Sensing Image Building Extraction and Change Detection with Foundation Model

The intelligent interpretation of buildings plays a significant role in urban planning and management, macroeconomic analysis, population dynamics, etc. Remote sensing image building interpretation primarily encompasses building extraction and change detection. However, current methodologies often treat these two tasks as separate entities, thereby failing to leverage shared knowledge. Moreover, the complexity and diversity of remote sensing image scenes pose additional challenges, as most algorithms are designed to model individual small datasets, thus lacking cross-scene generalization. In this paper, we propose a comprehensive remote sensing image building understanding model, termed RSBuilding, developed from the perspective of the foundation model. RSBuilding is designed to enhance cross-scene generalization and task universality. Specifically, we extract image features based on the prior knowledge of the foundation model and devise a multi-level feature sampler to augment scale information. To unify task representation and integrate image spatiotemporal clues, we introduce a cross-attention decoder with task prompts. Addressing the current shortage of datasets that incorporate annotations for both tasks, we have developed a federated training strategy to facilitate smooth model convergence even when supervision for some tasks is missing, thereby bolstering the complementarity of different tasks. Our model was trained on a dataset comprising up to 245,000 images and validated on multiple building extraction and change detection datasets. The experimental results substantiate that RSBuilding can concurrently handle two structurally distinct tasks and exhibits robust zero-shot generalization capabilities.

cs.CV↗

arXiv2023

Unleashing the Potential of Li-Metal Batteries A Breakthrough Ultra-High Room-Temperature Ionic Conductivity Composite Solid-State Electrolyte

The solid-state electrolyte is critical for achieving next-generation high energy density and high-safety batteries. Solid polymer electrolytes (SPEs) possess great potential for commercial application owing to their compatibility with the existing manufacturing systems. However, unsatisfactory room-temperature ionic conductivity severely limits its application. Herein, an ultra-high room-temperature ionic conductivity composite solid-state electrolyte (CSE) is prepared by introducing an appropriate amount of SiO2 nanosphere to the PVDF-HFP matrix. By doing this, the polymer particles are divided and surrounded by SiO2. And the interface amount is maximized resulting in the high ionic conductivity of 1.35 mS cm-1 under room temperature. In addition, the CSE shows a wide electrochemical window of 4.95 V and a moderate Li+ transference number of 0.44. The CSE demonstrates good stability with Li anode, with Li symmetric cells that could cycle 1000 h at a current density of 0.2 mA cm-2. The full cell assembled with LiFePO4 (LFP) and Li metal displays a high reversible specific capacity of 157.8 mAh g-1 at 0.1C, and it could maintain 92.9% of initial capacity after 300 cycles at 3C. Moreover, the strategy is applied in solid-state sodium/potassium batteries and displays excellent performance.

cond-mat.mtrl-sci↗

arXiv2020

HS-ResNet: Hierarchical-Split Block on Convolutional Neural Network

This paper addresses representational block named Hierarchical-Split Block, which can be taken as a plug-and-play block to upgrade existing convolutional neural networks, improves model performance significantly in a network. Hierarchical-Split Block contains many hierarchical split and concatenate connections within one single residual block. We find multi-scale features is of great importance for numerous vision tasks. Moreover, Hierarchical-Split block is very flexible and efficient, which provides a large space of potential network architectures for different applications. In this work, we present a common backbone based on Hierarchical-Split block for tasks: image classification, object detection, instance segmentation and semantic image segmentation/parsing. Our approach shows significant improvements over all these core tasks in comparison with the baseline. As shown in Figure1, for image classification, our 50-layers network(HS-ResNet50) achieves 81.28% top-1 accuracy with competitive latency on ImageNet-1k dataset. It also outperforms most state-of-the-art models. The source code and models will be available on: https://github.com/PaddlePaddle/PaddleClas

cs.CV↗

arXiv2019

Learning from Large-scale Noisy Web Data with Ubiquitous Reweighting for Image Classification

Many advances of deep learning techniques originate from the efforts of addressing the image classification task on large-scale datasets. However, the construction of such clean datasets is costly and time-consuming since the Internet is overwhelmed by noisy images with inadequate and inaccurate tags. In this paper, we propose a Ubiquitous Reweighting Network (URNet) that learns an image classification model from large-scale noisy data. By observing the web data, we find that there are five key challenges, i.e., imbalanced class sizes, high intra-classes diversity and inter-class similarity, imprecise instances, insufficient representative instances, and ambiguous class labels. To alleviate these challenges, we assume that every training instance has the potential to contribute positively by alleviating the data bias and noise via reweighting the influence of each instance according to different class sizes, large instance clusters, its confidence, small instance bags and the labels. In this manner, the influence of bias and noise in the web data can be gradually alleviated, leading to the steadily improving performance of URNet. Experimental results in the WebVision 2018 challenge with 16 million noisy training images from 5000 classes show that our approach outperforms state-of-the-art models and ranks the first place in the image classification task.

cs.CV↗

arXiv2018

Hierarchical Deep Co-segmentation of Primary Objects in Aerial Videos

Primary object segmentation plays an important role in understanding videos generated by unmanned aerial vehicles. In this paper, we propose a large-scale dataset with 500 aerial videos and manually annotated primary objects. To the best of our knowledge, it is the largest dataset to date for primary object segmentation in aerial videos. From this dataset, we find most aerial videos contain large-scale scenes, small primary objects as well as consistently varying scales and viewpoints. Inspired by that, we propose a hierarchical deep co-segmentation approach that repeatedly divides a video into two sub-videos formed by the odd and even frames, respectively. In this manner, the primary objects shared by sub-videos can be co-segmented by training two-stream CNNs and finally refined within the neighborhood reversible flows. Experimental results show that our approach remarkably outperforms 17 state-of-the-art methods in segmenting primary objects in various types of aerial videos.

cs.CV↗