papers

Publications (26)

cs.LG2026

DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders

Xu Wang, Bingqing Jiang, Yu Wan +3

Sparse autoencoders (SAEs) have become a standard tool for mechanistic interpretability in autoregressive large language models (LLMs), enabling researchers to extract sparse, huma…

cond-mat.mes-hall2014

Selective molecular capture mechanism in carbon nanotube networks

Yu Wan, Jun Guan, Xudong Yang +2

Recent air pollution issues have raised significant attention to develop efficient air filters, and one of the most promising candidates is that enabled by nanofibers. We explore h…

cs.CL2025

CultureSynth: A Hierarchical Taxonomy-Guided and Retrieval-Augmented Framework for Cultural Question-Answer Synthesis

Xinyu Zhang, Pei Zhang, Shuang Luo +4

Cultural competence, defined as the ability to understand and adapt to multicultural contexts, is increasingly vital for large language models (LLMs) in global environments. While…

cs.CL2026

Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models

Boyi Deng, Xu Wang, Yaoning Wang +15

Large language models have achieved remarkable capabilities across diverse tasks, yet their internal decision-making processes remain largely opaque, limiting our ability to inspec…

cs.CL2026

Towards Cross-lingual Values Judgment: A Consensus-Pluralism Perspective

Yukun Chen, Xinyu Zhang, Boyi Deng +6

As large language models (LLMs) are employed worldwide, existing evaluation paradigms for their multilingual capabilities primarily focus on factual task performance, neglecting th…

cs.CL2023

PolyLM: An Open Source Polyglot Large Language Model

Xiangpeng Wei, Haoran Wei, Huan Lin +15

Large language models (LLMs) demonstrate remarkable ability to comprehend, reason, and generate following nature language instructions. However, the development of LLMs has been pr…

cs.CL2023

Alibaba-Translate China's Submission for WMT 2022 Metrics Shared Task

Yu Wan, Keqin Bao, Dayiheng Liu +5

In this report, we present our submission to the WMT 2022 Metrics Shared Task. We build our system based on the core idea of UNITE (Unified Translation Evaluation), which unifies s…

cs.CL2020

Self-Paced Learning for Neural Machine Translation

Yu Wan, Baosong Yang, Derek F. Wong +4

Recent studies have proven that the training of neural machine translation (NMT) can be facilitated by mimicking the learning process of humans. Nevertheless, achievements of such…

cs.CL2026

SASFT: Sparse Autoencoder-guided Supervised Finetuning to Mitigate Unexpected Code-Switching in LLMs

Boyi Deng, Yu Wan, Baosong Yang +3

Large Language Models (LLMs) have impressive multilingual capabilities, but they suffer from unexpected code-switching, also known as language mixing, which involves switching to u…

cs.CL2022

RMBR: A Regularized Minimum Bayes Risk Reranking Framework for Machine Translation

Yidan Zhang, Yu Wan, Dayiheng Liu +2

Beam search is the most widely used decoding method for neural machine translation (NMT). In practice, the top-1 candidate with the highest log-probability among the n candidates i…

cs.CV2023

A Unified Framework for Multimodal, Multi-Part Human Motion Synthesis

Zixiang Zhou, Yu Wan, Baoyuan Wang

The field has made significant progress in synthesizing realistic human motion driven by various modalities. Yet, the need for different methods to animate various body parts accor…

cs.CL2022

UniTE: Unified Translation Evaluation

Yu Wan, Dayiheng Liu, Baosong Yang +4

Translation quality evaluation plays a crucial role in machine translation. According to the input format, it is mainly separated into three tasks, i.e., reference-only, source-onl…

cs.CL2019

Unsupervised Neural Dialect Translation with Commonality and Diversity Modeling

Yu Wan, Baosong Yang, Derek F. Wong +3

As a special machine translation task, dialect translation has two main characteristics: 1) lack of parallel training corpus; and 2) possessing similar grammar between two sides of…

cs.CL2025

Qwen3Guard Technical Report

Haiquan Zhao, Chenhan Yuan, Fei Huang +40

As large language models (LLMs) become more capable and widely used, ensuring the safety of their outputs is increasingly critical. Existing guardrail models, though useful in stat…

cs.CL2025

P-MMEval: A Parallel Multilingual Multitask Benchmark for Consistent Evaluation of LLMs

Yidan Zhang, Yu Wan, Boyi Deng +6

Recent advancements in large language models (LLMs) showcase varied multilingual capabilities across tasks like translation, code generation, and reasoning. Previous assessments of…

cs.CL2022

Attention Mechanism with Energy-Friendly Operations

Yu Wan, Baosong Yang, Dayiheng Liu +5

Attention mechanism has become the dominant module in natural language processing models. It is computationally intensive and depends on massive power-hungry multiplications. In th…

cs.CL2025

Qwen3 Technical Report

An Yang, Anfeng Li, Baosong Yang +57

In this work, we present Qwen3, the latest version of the Qwen model family. Qwen3 comprises a series of large language models (LLMs) designed to advance performance, efficiency, a…

cs.CV2023

AvatarGPT: All-in-One Framework for Motion Understanding, Planning, Generation and Beyond

Zixiang Zhou, Yu Wan, Baoyuan Wang

Large Language Models(LLMs) have shown remarkable emergent abilities in unifying almost all (if not every) NLP tasks. In the human motion-related realm, however, researchers still…

cs.CV2026

CoRE-UIR: Prior-guided common and residual experts for efficient all-in-one remote sensing image restoration

Zaiyan Zhang, Qiangqiang Yuan, Jie Li +5

The paper introduces CoRE-UIR, a prior‑guided framework that separates restoration into a common dense expert and low‑rank residual experts to efficiently handle multiple degradati…

#remote sensing#image restoration#all‑in‑one restoration#degradation prior
cs.CL2023

Alibaba-Translate China's Submission for WMT 2022 Quality Estimation Shared Task

Keqin Bao, Yu Wan, Dayiheng Liu +5

In this paper, we present our submission to the sentence-level MQM benchmark at Quality Estimation Shared Task, named UniTE (Unified Translation Evaluation). Specifically, our syst…

cs.CL2022

RoBLEURT Submission for the WMT2021 Metrics Task

Yu Wan, Dayiheng Liu, Baosong Yang +6

In this paper, we present our submission to Shared Metrics Task: RoBLEURT (Robustly Optimizing the training of BLEURT). After investigating the recent advances of trainable metrics…

eess.SP2025

Reconfigurable Intelligent Surface-Enhanced Satellite Networks: Deployment Strategies, Key Capabilities, Practical Solutions, and Future Directions

Ziyuan Zheng, Xiangyu Li, Shirui Zuo +4

Satellite networks promise wide-area 6G coverage but face two persistent barriers: blockage-induced service discontinuities and increasingly stringent spectrum coexistence across s…

cs.CL2025

Qwen2.5 Technical Report

Qwen, :, An Yang +41

In this report, we introduce Qwen2.5, a comprehensive series of large language models (LLMs) designed to meet diverse needs. Compared to previous iterations, Qwen 2.5 has been sign…

cs.CL2024

Qwen2 Technical Report

An Yang, Baosong Yang, Binyuan Hui +59

This report introduces the Qwen2 series, the latest addition to our large language models and large multimodal models. We release a comprehensive suite of foundational and instruct…

cs.CL2025

Unveiling Language-Specific Features in Large Language Models via Sparse Autoencoders

Boyi Deng, Yu Wan, Yidan Zhang +2

The mechanisms behind multilingual capabilities in Large Language Models (LLMs) have been examined using neuron-based or internal-activation-based methods. However, these methods o…

cs.CL2023

Towards Fine-Grained Information: Identifying the Type and Location of Translation Errors

Keqin Bao, Yu Wan, Dayiheng Liu +5

Fine-grained information on translation errors is helpful for the translation evaluation community. Existing approaches can not synchronously consider error position and type, fail…