RW
Rongxiang Weng
cs.CLcs.AIcs.LGcs.DCcs.CVcs.MMcs.SDcs.SE
On Valency
published · living versionsW_acjnt3k5·v1 · currentpublished
SAPD: Learning from Agent Experience without Environment Interaction
with Juncheng Diao, Haibin Wang, Wei Shi, Yifan Ding +2
1 version
W_kbpfrmbk·v1published
Preprints & journals
52 papers in the corpus · 2017–2026SAPD: Learning from Agent Experience without Environment Interaction2610.27847v1 · Juncheng Diao, Haibin Wang, Wei Shi et al.2026 · 0 citationsarXivon Valency
A Fisher-Geometric View of Multi-Teacher On-Policy Distillation2610.26525v1 · Liu Kaiyuan, Zhuang Ziyuan, Ma Haoxuan et al.2026 · 0 citationsarXivon Valency
What RL Brings to Reasoning: A Few Decisions the Base Model Would Not Make2610.24663v1 · Siyu Zhang, Yuquan Lu, Yoshua Y. Li et al.2026 · 0 citationsarXivon Valency
Better Supervision Is Nearby: Neighborhood On-Policy Self-Distillation2609.39687v1 · Xincheng Wei, Yifan Ding, Yoshua Li et al.2026 · 0 citationsarXiv
Learning What to Practice: Diagnosis-Guided Self-Evolution for Language Models2609.00768v2 · Xincheng Wei, Yifan Ding, Fucheng Xiong et al.2026 · 0 citationsarXiv
RecurSE: Bounded Recursive Self-Evaluation for LLM Rubric Judges2608.24231v1 · Kaiyuan Liu, Ziyuan Zhuang, Rongxiang Weng et al.2026 · 0 citationsarXiv
SAF-OPD: Stable Advantage Fusion for On-Policy Distillation2607.29209v1 · Yifan Ding, Xincheng Wei, Yoshua Y. Li et al.2026 · 0 citationsarXiv
ACE: Pluggable Adaptive Context Elasticizer across Agents2606.31564v1 · Ning Liao, Zihao Long, Xiaoxing Wang et al.2026 · 0 citationsarXiv
CuraWeb: Joint Optimization of Quality, Redundancy, and Diversity for Web-Scale Pretraining Data2607.22662v1 · Peiguang Li, Yongwei Zhou, Juncheng Diao et al.2026 · 0 citationsarXiv
HIPIF: Hierarchical Planning and Information Folding for Long-Horizon LLM Agent Learning2606.10507v1 · Juncheng Diao, Zhicong Lu, Peiguang Li et al.2026 · 0 citationsarXiv
Predictable Scaling Laws of Optimal Hyperparameters for LLM Continued Pre-training2606.05610v1 · Yongwei Zhou, Juncheng Diao, Junlin Shang et al.2026 · 0 citationsarXiv
LANG: Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint Guidance2605.22567v1 · Yuchun Fan, Bei Li, Peiguang Li et al.2026 · 0 citationsarXiv
Multi-Objective and Mixed-Reward Reinforcement Learning via Reward-Decorrelated Policy Optimization2605.13641v1 · Yang Bai, Kaiyuan Liu, Ziyuan Zhuang et al.2026 · 0 citationsarXiv
Prefix Teach, Suffix Fade: Local Teachability Collapse in Strong-to-Weak On-Policy Distillation2605.13643v2 · Kaiyuan Liu, Ziyuan Zhuang, Yang Bai et al.2026 · 0 citationsarXiv
LongCat-Flash-Thinking-2601 Technical Report2601.16725v2 · Meituan LongCat Team, Anchun Gui, Bei Li et al.2026 · 0 citationsarXiv
Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from Text2601.10355v1 · Zhihao Xu, Rumei Li, Jiahuan Li et al.2026 · 0 citationsarXiv
Efficient Context Scaling with LongCat ZigZag Attention2512.23966v2 · Chen Zhang, Yang Bai, Jiahuan Li et al.2025 · 0 citationsarXiv
LongCat-Flash-Omni Technical Report2511.00279v2 · Meituan LongCat Team, Bairui Wang, Bayan et al.2025 · 0 citationsarXiv
A Survey on LLM Mid-Training2510.23081v2 · Chengying Tu, Xuemiao Zhang, Rongxiang Weng et al.2025 · 0 citationsarXiv
AdaR: A Framework for Equipping LLMs with Adaptive Reasoning2510.04617v3 · Zhejian Lai, Xiang Geng, Zhijun Wang et al.2025 · 0 citationsarXiv
Expanding Reasoning Potential in Foundation Model by Learning Diverse Chains of Thought Patterns2509.21124v3 · Xuemiao Zhang, Can Ren, Chengying Tu et al.2025 · 0 citationsarXiv
Introducing LongCat-Flash-Thinking: A Technical Report2509.18883v2 · Meituan LongCat Team, Anchun Gui, Bei Li et al.2025 · 0 citationsarXiv
OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generation2509.03498v3 · Han Li, Xinyu Peng, Yaoming Wang et al.2025 · 0 citationsarXiv
LongCat-Flash Technical Report2509.01322v2 · Meituan LongCat Team, Bayan, Bei Li et al.2025 · 1 citationarXiv
LinkQA: Synthesizing Diverse QA from Multiple Seeds Strongly Linked by Knowledge Points2508.01317v2 · Xuemiao Zhang, Can Ren, Chengying Tu et al.2025 · 0 citationsarXiv
Large-Scale Diverse Synthesis for Mid-Training2508.01326v1 · Xuemiao Zhang, Chengying Tu, Can Ren et al.2025 · 0 citationsarXiv
Libra: Assessing and Improving Reward Model by Learning to Think2507.21645v1 · Meng Zhou, Bei Li, Jiahao Liu et al.2025 · 0 citationsarXiv
XBOUND: Exploring Capability Boundaries of Device-Control Agents at the State Level2505.21279v2 · Shaoqing Zhang, Kehai Chen, Zhuosheng Zhang et al.2025 · 0 citationsarXiv
Two Minds Better Than One: Collaborative Reward Modeling for LLM Alignment2505.10597v3 · Jiazheng Zhang, Wenqing Jing, Zizhuo Zhang et al.2025 · 0 citationsarXiv
Investigating and Scaling up Code-Switching for Multilingual Language Model Pre-Training2504.01801v2 · Zhijun Wang, Jiahuan Li, Hao Zhou et al.2025 · 3 citationsarXiv
FRAME: Boosting LLMs with A Four-Quadrant Multi-Stage Pretraining Strategy2502.05551v4 · Xuemiao Zhang, Feiyu Duan, Liangyu Xu et al.2025 · 0 citationsarXiv
Preference Curriculum: LLMs Should Always Be Pretrained on Their Preferred Data2501.13126v2 · Xuemiao Zhang, Liangyu Xu, Feiyu Duan et al.2025 · 3 citationsarXiv
Look Before You Leap: Enhancing Attention and Vigilance Regarding Harmful Content with GuidelineLLM2412.10423v2 · Shaoqing Zhang, Zhuosheng Zhang, Kehai Chen et al.2024 · 0 citationsarXiv
Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision2411.16579v1 · Zhiheng Xi, Dingwen Yang, Jixuan Huang et al.2024 · 0 citationsarXiv
Multi-Programming Language Sandbox for LLMs2410.23074v2 · Shihan Dou, Jiazheng Zhang, Jianxiang Zang et al.2024 · 1 citationarXiv
Length Desensitization in Direct Preference Optimization2409.06411v2 · Wei Liu, Yang Bai, Chengcheng Han et al.2024 · 0 citationsarXiv
The Rise and Potential of Large Language Model Based Agents: A Survey2309.07864v3 · Zhiheng Xi, Wenxiang Chen, Xin Guo et al.2023 · 960 citationsarXiv
Secrets of RLHF in Large Language Models Part I: PPO2307.04964v2 · Rui Zheng, Shihan Dou, Songyang Gao et al.2023 · 26 citationsarXiv
Towards Reliable Neural Machine Translation with Consistency-Aware Meta-Learning2303.10966v2 · Rongxiang Weng, Qiang Wang, Wensen Cheng et al.2023 · 3 citationsarXiv
Learning Decoupled Retrieval Representation for Nearest Neighbour Neural Machine Translation2209.08738v3 · Qiang Wang, Rongxiang Weng, Ming Chen2022 · 4 citationsarXiv
Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translation2204.06812v1 · Xiangpeng Wei, Heng Yu, Yue Hu et al.2022 · 27 citationsarXiv
Uncertainty-Aware Semantic Augmentation for Neural Machine Translation2010.04411v1 · Xiangpeng Wei, Heng Yu, Yue Hu et al.2020 · 21 citationsarXiv
On Learning Universal Representations Across Languages2007.15960v4 · Xiangpeng Wei, Rongxiang Weng, Yue Hu et al.2020 · 63 citationsarXiv
Multiscale Collaborative Deep Models for Neural Machine Translation2004.14021v3 · Xiangpeng Wei, Heng Yu, Yue Hu et al.2020 · 27 citationsarXiv
AR: Auto-Repair the Synthetic Data for Neural Machine Translation2004.02196v1 · Shanbo Cheng, Shaohui Kuang, Rongxiang Weng et al.2020 · 4 citationsarXiv
GRET: Global Representation Enhanced Transformer2002.10101v1 · Rongxiang Weng, Haoran Wei, Shujian Huang et al.2020 · 11 citationsarXiv
Acquiring Knowledge from Pre-trained Model to Neural Machine Translation1912.01774v1 · Rongxiang Weng, Heng Yu, Shujian Huang et al.2019 · 67 citationsarXiv
Improving Neural Machine Translation with Pre-trained Representation1908.07688v1 · Rongxiang Weng, Heng Yu, Shujian Huang et al.2019 · 5 citationsarXiv
Learning Representation Mapping for Relation Detection in Knowledge Base Question Answering1907.07328v1 · Peng Wu, Shujian Huang, Rongxiang Weng et al.2019 · 28 citationsarXiv
Correct-and-Memorize: Learning to Translate from Interactive Revisions1907.03468v2 · Rongxiang Weng, Hao Zhou, Shujian Huang et al.2019 · 17 citationsarXiv
Career total: 70 works. 52 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.