Explanipedia

Beyond Single-Reward: Multi-Pair, Multi-Perspective Preference Optimization for Machine Translation Open

Hao Wang, Linlong Xu, Heng Liu, Yangyang Liu, Xiaohu Zhao , et al. · 2025

Direct Preference Optimization (DPO) is a powerful paradigm for aligning Large Language Models (LLMs) to human preferences in Machine Translation (MT), but current methods are hindered by two fundamental challenges: (1) flawed reward signa…

Generative AI and Firm Productivity: Field Experiments in Online Retail Open

Lu Fang, Zhe Yuan, Kaifu Zhang, Dante Donati, Miklós Sárváry · 2025

We quantify the impact of Generative Artificial Intelligence (GenAI) on firm productivity through a series of large-scale randomized field experiments involving millions of users and products at a leading cross-border online retail platfor…

Enhanced morphology and conductivity in aerosol jet printing via optimization of print speed range under various deposition rate Open

Xuanbo Jiang, Zijun Yan, Yingjie Niu, Xuan Zhang, Teng Ma , et al. · 2025

Marco-Bench-MIF: On Multilingual Instruction-Following Capability of Large Language Models Open

Bo Zeng, Chenyang Lyu, Sinuo Liu, Mingyan Zeng, Minghao Wu , et al. · 2025

Instruction-following capability has become a major ability to be evaluated for Large Language Models (LLMs). However, existing datasets, such as IFEval, are either predominantly monolingual and centered on English or simply machine transl…

Strain rate dependent material removal mechanism and surface morphology formation mechanism for high strength CFRTP Open

Kuangqing Hu, Shunuan Liu, Shiming Liang, Bin Luo, Kaifu Zhang · 2025

Rethinking Multilingual Vision-Language Translation: Dataset, Evaluation, and Adaptation Open

Xintong Wang, Jingheng Pan, Yixiao Liu, Zhao Xiao-hu, Chenyang Lyu , et al. · 2025

Vision-Language Translation (VLT) is a challenging task that requires accurately recognizing multilingual text embedded in images and translating it into the target language with the support of visual context. While recent Large Vision-Lan…

Multimodal Tabular Reasoning with Privileged Structured Information Open

Junpeng Jiang, Yu Xia, Hailong Sun, Shiyin Lu, Qing-Guo Chen , et al. · 2025

Tabular reasoning involves multi-step information extraction and logical inference over tabular data. While recent advances have leveraged large language models (LLMs) for reasoning over structured tables, such high-quality textual represe…

Investigation on Hole Quality and Tool Wear of <span>CFRP</span> Drilling With Cryogenic‐Minimal Quantity Lubrication Open

Tao Wang, Shunuan Liu, Zhijian Meng, Kuangqing Hu, Bin Luo , et al. · 2025

Carbon fiber reinforced polymer (CFRP) is extensively utilized in various fields, including aerospace and automotive industries, where drilling serves as a common method for mechanical assembly. However, the inherent anisotropy and inhomog…

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Open

Baolin Zheng, Guanlin Chen, Hang Zhong, Qingyang Teng, Yingshui Tan , et al. · 2025

Despite their remarkable achievements and widespread adoption, Multimodal Large Language Models (MLLMs) have revealed significant security vulnerabilities, highlighting the urgent need for robust safety evaluation benchmarks. Existing MLLM…

Beyond Safe Answers: A Benchmark for Evaluating True Risk Awareness in Large Reasoning Models Open

Boyang Zheng, Boren Zheng, Kankan Cao, Yingshui Tan, Zhendong Liu , et al. · 2025

Despite the remarkable proficiency of \textit{Large Reasoning Models} (LRMs) in handling complex reasoning tasks, their reliability in safety-critical scenarios remains uncertain. Existing evaluations primarily assess response-level safety…

TransBench: Benchmarking Machine Translation for Industrial-Scale Applications Open

Haijun Li, Tianqi Shi, Zifu Shang, Yuxuan Han, Xin Zhao , et al. · 2025

Machine translation (MT) has become indispensable for cross-border communication in globalized industries like e-commerce, finance, and legal services, with recent advancements in large language models (LLMs) significantly enhancing transl…

Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities Open

Xinjie Zhang, Jintao Guo, Shanshan Zhao, M.W. Fu, Lunhao Duan , et al. · 2025

Recent years have seen remarkable progress in both multimodal understanding models and image generation models. Despite their respective successes, these two domains have evolved independently, leading to distinct architectural paradigms: …

Effect of cooling temperature on machinability and hole quality in cryogenic drilling of CFRP/Ti stacks Open

Shunuan Liu, Zhijian Meng, Shiming Liang, Tao Wang, Hao Niu , et al. · 2025

Carbon fiber reinforced polymer/titanium alloy (CFRP/Ti) stacks are extensively employed in modern aircraft owing to their outstanding mechanical properties. At present, cryogenic machining is considered an effective method for reducing dr…

The Bitter Lesson Learned from 2,000+ Multilingual Benchmarks Open

Minghao Wu, Weixuan Wang, Sinuo Liu, Haowen Yin, Xintong Wang , et al. · 2025

As large language models (LLMs) continue to advance in linguistic capabilities, robust multilingual evaluation has become essential for promoting equitable technological progress. This position paper examines over 2,000 multilingual (non-E…

New Trends for Modern Machine Translation with Large Reasoning Models Open

Sinuo Liu, Chenyang Lyu, Minghao Wu, Longyue Wang, Weihua Luo , et al. · 2025

Recent advances in Large Reasoning Models (LRMs), particularly those leveraging Chain-of-Thought reasoning (CoT), have opened brand new possibility for Machine Translation (MT). This position paper argues that LRMs substantially transforme…

Marco-o1 v2: Towards Widening The Distillation Bottleneck for Reasoning Models Open

Haowen Yin, Yu Zhao, Minghao Wu, Xuanfan Ni, Baoqing Zeng , et al. · 2025

Large Reasoning Models(LRMs) such as OpenAI o1 and DeepSeek-R1 have shown remarkable reasoning capabilities by scaling test-time compute and generating long Chain-of-Thought(CoT). Distillation--post-training on LRMs-generated data--is a st…

Towards Lightweight, Adaptive and Attribute-Aware Multi-Aspect Controllable Text Generation with Large Language Models Open

Chenyu Zhu, Yefeng Liu, Chenyang Lyu, Xue Yang, Guanhua Chen , et al. · 2025

Multi-aspect controllable text generation aims to control text generation in attributes from multiple aspects, making it a complex but powerful task in natural language processing. Supervised fine-tuning methods are often employed for this…

Thermally activated fluorescence in 9,10-DPA single crystals enabling high-performance fast neutron detection Open

Ying Wang, Lingyan Xu, Liang Lu, Zhentao Qin, Zhuochen Cai , et al. · 2025

Organic scintillators occupy a significant niche in the realm of fast neutron detection. Nevertheless, the cultivation of large-sized and high-quality organic single crystals has persistently posed a formidable challenge. 9,10-diphenylanth…

Multi-objective optimal design for flexible bio-inspired meta-structure with ultra-broadband microwave absorption and thin thickness Open

Mengfei Feng, Sheng Liu, Hui Cheng, Kaifu Zhang, Yuan Li , et al. · 2025

Chinese SafetyQA: A Safety Short-form Factuality Benchmark for Large Language Models Open

Yingshui Tan, Boren Zheng, Boyang Zheng, Kankan Cao, He Jing , et al. · 2025

Enhanced Morphology and Conductivity in Aerosol Jet Printing Via Optimization of Print Speed Range Under Various Deposition Rate Open

Xuanbo Jiang, Zijun Yan, Yingjie Niu, Xuan Zhang, Teng Ma , et al. · 2025

Investigation on Static and Fatigue Performance of Cfrp/Al-Alloy Interference Bolted Joint Considering the Influence of Hole-Axis Error Open

Caoyang Wang, Hui Cheng, Wenlong Hu, Yuan Yuan Li, Kaifu Zhang , et al. · 2025

(Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Texts Open

Minghao Wu, Jiahao Xu, Yulin Yuan, Gholamreza Haffari, Lili Wan , et al. · 2025

Literary translations remains one of the most challenging frontiers in machine translation due to the complexity of capturing figurative language, cultural nuances, and unique stylistic elements. In this work, we introduce TransAgents, a n…

Marco-Bench-MIF: On Multilingual Instruction-Following Capability of Large Language Open

Bo Zeng, Chenyang Lyu, Sinuo Liu, Mingyan Zeng, Minghao Wu , et al. · 2025

Marco-LLM: Bridging Languages via Massive Multilingual Training for Cross-Lingual Enhancement Open

Lingfeng Ming, Bo Zeng, Chenyang Lyu, Tianqi Shi, Yu Zhao , et al. · 2024

Large Language Models (LLMs) have achieved remarkable progress in recent years; however, their excellent performance is still largely limited to major world languages, primarily English. Many LLMs continue to face challenges with multiling…

PMMT: Preference Alignment in Multilingual Machine Translation via LLM Distillation Open

Shuqiao Sun, Yutong Yao, Pei‐Wen Wu, Feijun Jiang, Kaifu Zhang · 2024

Translation is important for cross-language communication, and many efforts have been made to improve its accuracy. However, less investment is conducted in aligning translations with human preferences, such as translation tones or styles.…

Fatigue Damage Monitoring of Composite Structures Based on Lamb Wave Propagation and Multi-Feature Fusion Open

Feiting Zhang, Kaifu Zhang, Hui Cheng, Dongyue Gao, Kaiyu Cai · 2024

To address the challenges associated with fatigue damage monitoring in load-bearing composite structures, we developed a method that utilizes Lamb wave propagation and partial least squares regression (PLSR) for effective monitoring. Initi…

Ultrasonic Guided Wave Health Monitoring of High-Temperature Aircraft Structures Based on Variational Mode Decomposition and Fuzzy Entropy Open

Feiting Zhang, Kaifu Zhang, Hui Cheng, Dongyue Gao, Kun Cai · 2024

This paper presents an innovative approach to high-temperature health monitoring of aircraft structures utilizing an ultrasonic guided wave transmission and reception system integrated with a zirconia heat buffer layer. Aiming to address t…

Enhanced aerosol-jet printing using annular acoustic field for high resolution and minimal overspray Open

Teng Ma, Yuan Li, Hui Cheng, Yingjie Niu, Zhenxiang Xiong , et al. · 2024

Ovis: Structural Embedding Alignment for Multimodal Large Language Model Open

Shiyin Lu, Yang Li, Qing-Guo Chen, Zhao Xu, Weihua Luo , et al. · 2024

Current Multimodal Large Language Models (MLLMs) typically integrate a pre-trained LLM with another pre-trained vision transformer through a connector, such as an MLP, endowing the LLM with visual capabilities. However, the misalignment be…

Kaifu Zhang YOU? Author Swipe