WJ
Wenxiang Jiao
cs.CLcs.AIcs.LGcs.SEcs.CVcs.MMAmplifiers, ElectronicAtmospherecs.CRcs.IR
On Valency
published · living versionsW_evw6musx·v1 · currentpublished
Harness-S: Learning from Sibling Harnesses for Generalizable Agent Training
with Kangning Zhang, Bowen Fang, Shuai Shao, Jiachen Zhu +6
1 version
Preprints & journals
57 papers in the corpus · 2014–2026FleetPilot: Fine-Grained Steering Empowers Real-World LLM Personalization2610.14970v1 · Kounianhua Du, Jianxing Liu, Kangning Zhang et al.2026 · 0 citationsarXiv
Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectories2608.02276v1 · Shuai Shao, Kangning Zhang, Qingyao Li et al.2026 · 0 citationsarXiv
LoopTool: Closing the Data-Training Loop for Robust LLM Tool Calls2511.09148v2 · Kangning Zhang, Wenxiang Jiao, Kounianhua Du et al.2025 · 1 citationarXiv
Fints: Efficient Inference-Time Personalization for LLMs with Fine-Grained Instance-Tailored Steering2510.27206v1 · Kounianhua Du, Jianxing Liu, Kangning Zhang et al.2025 · 0 citationsarXiv
DeepCompress: A Dual Reward Strategy for Dynamically Exploring and Compressing Reasoning Chains2510.27419v2 · Tian Liang, Wenxiang Jiao, Zhiwei He et al.2025 · 0 citationsarXiv
DeepAgent: A General Reasoning Agent with Scalable Toolsets2510.21618v3 · Xiaoxi Li, Wenxiang Jiao, Jiarui Jin et al.2025 · 5 citationsarXiv
Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards2510.07774v3 · Youliang Yuan, Qiuyang Mang, Jingbang Chen et al.2025 · 0 citationsarXiv
Benchmarking Chinese Commonsense Reasoning with a Multi-hop Reasoning Perspective2510.08800v1 · Wangjie You, Xusheng Wang, Xing Wang et al.2025 · 0 citationsarXiv
REA-RL: Reflection-Aware Online Reinforcement Learning for Efficient Reasoning2505.19862v2 · Hexuan Deng, Wenxiang Jiao, Xuebo Liu et al.2025 · 0 citationsarXiv
Towards Evaluating Proactive Risk Awareness of Multimodal Language Models2505.17455v2 · Youliang Yuan, Wenxiang Jiao, Yuejin Xie et al.2025 · 1 citationarXiv
Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought2505.15431v3 · Tencent Hunyuan Team: Ao Liu, Botong Zhou, Can Xu et al.2025 · 0 citationsarXiv
Findings of the WMT 2024 Shared Task on Discourse-Level Literary Translation2412.11732v1 · Longyue Wang, Siyou Liu, Chenyang Lyu et al.2024 · 4 citationsarXiv
DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization2411.14055v2 · Hexuan Deng, Wenxiang Jiao, Xuebo Liu et al.2024 · 0 citationsarXiv
On the Shortcut Learning in Multilingual Neural Machine Translation2411.10581v1 · Wenxuan Wang, Wenxiang Jiao, Jen-tse Huang et al.2024 · 6 citationsarXiv
NewTerm: Benchmarking Real-Time New Terms for Large Language Models with Annual Updates2410.20814v1 · Hexuan Deng, Wenxiang Jiao, Xuebo Liu et al.2024 · 2 citationsarXiv
Chain-of-Jailbreak Attack for Image Generation Models via Editing Step by Step2410.03869v2 · Wenxuan Wang, Kuiyi Gao, Youliang Yuan et al.2024 · 0 citationsarXiv
Learning to Ask: When LLM Agents Meet Unclear Instruction2409.00557v4 · Wenxuan Wang, Juluan Shi, Zixuan Ling et al.2024 · 4 citationsarXiv
Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training2407.09121v2 · Youliang Yuan, Wenxiang Jiao, Wenxuan Wang et al.2024 · 7 citationsarXiv
CoAct: A Global-Local Hierarchy for Autonomous Agent Collaboration2406.13381v1 · Xinming Hou, Mingming Yang, Wenxiang Jiao et al.2024 · 1 citationarXiv
Improving Gloss-free Sign Language Translation by Reducing Representation Density2405.14312v2 · Jinhui Ye, Xing Wang, Wenxiang Jiao et al.2024 · 6 citationsarXiv
How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments2403.11807v7 · Jen-tse Huang, Eric John Li, Man Ho Lam et al.2024 · 12 citationsarXiv
Unsupervised Sign Language Translation and Generation2402.07726v1 · Zhengsheng Guo, Zhiwei He, Wenxiang Jiao et al.2024 · 6 citationsarXiv
Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model2401.12873v3 · Zhiwei He, Xing Wang, Wenxiang Jiao et al.2024 · 8 citationsarXiv
LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models2401.00757v3 · Yuxuan Wan, Wenxuan Wang, Yiliu Yang et al.2024 · 16 citationsarXiv
Identifying the Achilles' Heel: An Iterative Method for Dynamically Uncovering Factual Errors in Large Language Models2401.00761v2 · Wenxuan Wang, Yuk-Kit Chan, Zixuan Ling et al.2024 · 3 citationsarXiv
Leveraging Word Guessing Games to Assess the Intelligence of Large Language Models2310.20499v2 · Tian Liang, Zhiwei He, Jen-tse Huang et al.2023 · 1 citationarXiv
Not All Countries Celebrate Thanksgiving: On the Cultural Dominance in Large Language Models2310.12481v2 · Wenxuan Wang, Wenxiang Jiao, Jingyuan Huang et al.2023 · 35 citationsarXiv
All Languages Matter: On the Multilingual Safety of Large Language Models2310.00905v2 · Wenxuan Wang, Zhaopeng Tu, Chang Chen et al.2023 · 4 citationsarXiv
Who is ChatGPT? Benchmarking LLMs' Psychological Portrayal Using PsychoBench2310.01386v2 · Jen-tse Huang, Wenxuan Wang, Eric John Li et al.2023 · 9 citationsarXiv
GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher2308.06463v2 · Youliang Yuan, Wenxiang Jiao, Wenxuan Wang et al.2023 · 14 citationsarXiv
Emotionally Numb or Empathetic? Evaluating How LLMs Feel Using EmotionBench2308.03656v6 · Jen-tse Huang, Man Ho Lam, Eric John Li et al.2023 · 14 citationsarXiv
Revisiting the Reliability of Psychological Scales on Large Language Models2305.19926v5 · Jen-tse Huang, Wenxiang Jiao, Man Ho Lam et al.2023 · 10 citationsarXiv
Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate2305.19118v4 · Tian Liang, Zhiwei He, Wenxiang Jiao et al.2023 · 318 citationsarXiv
Cross-modality Data Augmentation for End-to-End Sign Language Translation2305.11096v4 · Jinhui Ye, Wenxiang Jiao, Xing Wang et al.2023 · 26 citationsarXiv
Exploring Human-Like Translation Strategy with Large Language Models2305.04118v3 · Zhiwei He, Tian Liang, Wenxiang Jiao et al.2023 · 101 citationsarXiv
ParroT: Translating during Chat using Large Language Models tuned with Human Translation and Feedback2304.02426v5 · Wenxiang Jiao, Jen-tse Huang, Wenxuan Wang et al.2023 · 28 citationsarXiv
ChatGPT or Grammarly? Evaluating ChatGPT on Grammatical Error Correction Benchmark2303.13648v1 · Haoran Wu, Wenxuan Wang, Yuxuan Wan et al.2023 · 51 citationsarXiv
Is ChatGPT A Good Translator? Yes With GPT-4 As The Engine2301.08745v4 · Wenxiang Jiao, Wenxuan Wang, Jen-tse Huang et al.2023 · 317 citationsarXiv
Adapters for Enhanced Modeling of Multilingual Knowledge and Text2210.13617v2 · Yifan Hou, Wenxiang Jiao, Meizhen Liu et al.2022 · 6 citationsarXiv
Tencent's Multilingual Machine Translation System for WMT22 Large-Scale African Languages2210.09644v1 · Wenxiang Jiao, Zhaopeng Tu, Jiarui Li et al.2022 · 4 citationsarXiv
Scaling Back-Translation with Domain Text Generation for Sign Language Gloss Translation2210.07054v2 · Jinhui Ye, Wenxiang Jiao, Xing Wang et al.2022 · 11 citationsarXiv
Understanding and Mitigating the Uncertainty in Zero-Shot Translation2205.10068v2 · Wenxuan Wang, Wenxiang Jiao, Shuo Wang et al.2022 · 4 citationsarXiv
Understanding and Improving Sequence-to-Sequence Pretraining for Neural Machine Translation2203.08442v1 · Wenxuan Wang, Wenxiang Jiao, Yongchang Hao et al.2022 · 31 citationsarXiv
Self-Training Sampling with Monolingual Data Uncertainty for Neural Machine Translation2106.00941v1 · Wenxiang Jiao, Xing Wang, Zhaopeng Tu et al.2021 · 30 citationsarXiv
Multi-Task Learning with Shared Encoder for Non-Autoregressive Machine Translation2010.12868v2 · Yongchang Hao, Shilin He, Wenxiang Jiao et al.2020 · 29 citationsarXiv
Data Rejuvenation: Exploiting Inactive Training Examples for Neural Machine Translation2010.02552v1 · Wenxiang Jiao, Xing Wang, Shilin He et al.2020 · 21 citationsarXiv
Exploiting Unsupervised Data for Emotion Recognition in Conversations2010.01908v2 · Wenxiang Jiao, Michael R. Lyu, Irwin King2020 · 15 citationsarXiv
Real-Time Emotion Recognition via Attention Gated Hierarchical Memory Network1911.09075v1 · Wenxiang Jiao, Michael R. Lyu, Irwin King2019 · 148 citationsarXiv
Improving Word Representations: A Sub-sampled Unigram Distribution for Negative Sampling1910.09362v1 · Wenxiang Jiao, Irwin King, Michael R. Lyu2019 · 0 citationsarXiv
PT-CoDE: Pre-trained Context-Dependent Encoder for Utterance-level Emotion Recognition1910.08916v1 · Wenxiang Jiao, Michael R. Lyu, Irwin King2019 · 6 citationsarXiv
Career total: 84 works. 57 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.