Huan Liu

Visible–infrared remote sensing image fusion for object detection based on hybrid-level dual-input Mamba fusion

zhengqun ren, Huan Liu, Guangli Ben, Qisheng Hao et autres

Existing visible–infrared fusion detectors often struggle to balance cross modal complementarity, redundancy, and conflict. Most multimodal Mamba methods pre-fuse the two modalities before state space modeling, causing complementary and conflicting cues to be jointly encoded and obscuring their sources and reliability during …

cn (code pays fourni par la source)

Data Assets and Corporate Continuous Innovation: Mechanisms of Robust Anchoring and Dynamic Reconstruction

Xue Guo, Bingjie Zhang, Huan Liu, Yanbo Wang

In the context of deepening data assetization, this paper explores the strategic role of data assets in sustaining corporate competitiveness. Utilizing a dataset of China’s A-share listed companies from 2010 to 2023, we examine the influence of data assets on continuous innovation …

cn (code pays fourni par la source)

On the Role of Anticausal Direction in LLM-based Data Synthesis

Bohan Jiang, Pingchuan Ma, Zhen Tan, Zhuoyu Shi et autres

Large Language Models (LLMs) are increasingly used to generate synthetic data. Most LLM-based data synthesis workflows are anticausal : the user injects Y into the prompt to enforce targeted generation of X (Y\rightarrow X). This anticausal direction seems contradictory to the natural …

us (code pays fourni par la source)

RelKD 2026: The Fourth International Workshop on Resource-Efficient Learning for Knowledge Discovery

Chuxu Zhang, Kaize Ding, Dongkuan Xu, Haoyu Wang et autres

us (code pays fourni par la source)

From Moderation to Mediation: Can LLMs Serve as Mediators in Online Flame Wars?

Dawei Li, Abdullah Alnaibari, Arslan Bisharat, Marco Tulio Rodríguez Sandoval et autres

us (code pays fourni par la source)

A Survey of Scaling in Large Language Model Reasoning

Zihan Chen, Song Wang, Zhen Tan, Xiaotian Fu et autres

The rapid advancements in large Language models (LLMs) have significantly enhanced their reasoning capabilities, driven by various strategies such as multi-agent collaboration. However, unlike the well-established performance improvements achieved through scaling data and model size, the scaling of reasoning in LLMs is …

us (code pays fourni par la source)

Accelerating Realization of Effective Capacity in Lightweight Vision Models via Self-Competitive Distillation

Weidong Zhang, Bing Li, Huan Liu, Pak Lun Kevin Ding et autres

We introduce Self-Competitive Distillation (SCD), a parameter-neutral training strategy aimed at influencing optimization dynamics without increasing model size or relying on external teachers. Two identical instances of the same architecture, initialized with different random seeds, are trained jointly and dynamically exchange asymmetric …

us (code pays fourni par la source)

Predictive modle for violence risk in hospitalized schizophrenia patients based on support vector machine

Huan Liu, Shi Peifang, Kun Zhang, Kang Li et autres

BackgroundThe violent aggressive behaviors of patients with schizophrenia usually have the characteristics of suddenness， unpredictability， high severity， and great difficulty in prevention. Early identification and accurate assessment of their risk of violent aggression have significant clinical significance.ObjectiveTo construct a predictive model for …

cn (code pays fourni par la source)

THE IMPACT OF CLIMATE RISK ON THE OPERATIONAL EFFICIENCY OF FISHERY ENTERPRISES: EVIDENCE FROM CHINA

L.L. SUN, Huan Liu, S.L. Qu

The marine environment is facing numerous challenges, and consequently the development of fishery enterprises is subject to significant risks.To analyze how climate risks affect the operational performance of fisheries companies, this research uses seven listed Chinese fishery enterprises as empirical subjects, collects …

cn, hu (code pays fourni par la source)

Human-AI Collaboration in Corporate Valuation: Experimental Evidence with a Valuation AI Agent

Huan Liu, Miao Liu, Zhizhe Liu, Danqing Mei

us, cn (code pays fourni par la source)

A Multi-Objective Reinforcement Learning Framework for Energy-Efficient Electric Bus Operations

Huan Liu, Wenjie Lu, Xiaonian Shan

In urban arterials, buses face dual constraints from signal-controlled intersections and bus stop dwell demands, and frequent start–stop cycles result in reduced operational efficiency and elevated energy consumption. To address this critical challenge, a sustainable eco-driving strategy integrating offline and online Reinforcement …

cn (code pays fourni par la source)

Physiological and transcriptomic analyses reveal the effect of exogenous chitosan oligosaccharides on ‘Harumi’ fruit resistance to Penicillium digitatum

Mingfei Zhang, Xu Zou, Jiahuan Liu, Yuping Wang et autres

cn (code pays fourni par la source)