WS
Wenbo Su
cs.CLcs.AIcs.LGcs.IRcs.CVcs.DCcs.SEcs.CR
On Valency
published · living versionsW_4y6r4vd4·v1 · currentpublished
HiLo-RD: Cross-Budget Self-Distillation for Masked Diffusion Language Models
with Xiang Li, Chengting Yu, Jungang Li, Yilun Zheng +3
1 version
W_anv4j92z·v1published
Preprints & journals
58 papers in the corpus · 2024–2026Socratic Skill Learning: Interleaving Teaching and Practice for Transferable Agent Skills2610.17860v1 · Letian Zhu, Han Li, Yifan Yao et al.2026 · 0 citationsarXiv
HappyWorld-Bench2609.24308v1 · Zhiqi Bai, Junai Cai, Yixin Chen et al.2026 · 0 citationsarXiv
PReM: Learning What to Preserve and When to Refresh for Context Compression2607.14327v1 · Bohan Yu, Lei Shen, Chenxi Zhou et al.2026 · 0 citationsarXiv
The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning2606.29526v1 · Jing Liang, Hongyao Tang, Yi Ma et al.2026 · 0 citationsarXiv
How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs2606.10646v1 · Zhichen Dong, Yang Li, Yuhan Sun et al.2026 · 0 citationsarXiv
TVIR: Building Deep Research Agents Towards Text-Visual Interleaved Report Generation2606.02320v2 · Xinkai Ma, Zhiqi Bai, Dingling Zhang et al.2026 · 0 citationsarXiv
YOCO++: Enhancing YOCO with KV Residual Connections for Efficient LLM Inference2604.13556v1 · You Wu, Ziheng Chen, Yizhen Zhang et al.2026 · 0 citationsarXiv
PoC: Performance-oriented Context Compression for Large Language Models via Performance Prediction2603.19733v1 · Runsong Zhao, Shilei Liu, Jiwei Tang et al.2026 · 0 citationsarXiv
Complementary RL: Towards Efficient Experience-Driven Agent Learning2603.17621v2 · Dilxat Muhtar, Jiashun Liu, Wei Gao et al.2026 · 0 citationsarXiv
SpiralFormer: Looped Transformers Can Learn Hierarchical Dependencies via Multi-Resolution Recursion2602.11698v2 · Chengting Yu, Xiaobo Shu, Yadao Wang et al.2026 · 0 citationsarXiv
Expert Divergence Learning for MoE-based Language Models2603.00054v1 · Jiaang Li, Haibin Chen, Langming Liu et al.2026 · 0 citationsarXiv
COMI: Coarse-to-fine Context Compression via Marginal Information Gain2602.01719v3 · Jiwei Tang, Shilei Liu, Zhicheng Zhang et al.2026 · 0 citationsarXiv
Data Distribution Matters: A Data-Centric Perspective on Context Compression for Large Language Model2602.01778v1 · Kangtao Lv, Jiwei Tang, Langming Liu et al.2026 · 0 citationsarXiv
Dissecting Outlier Dynamics in LLM NVFP4 Pretraining2602.02047v1 · Peijie Dong, Ruibo Fan, Yuechen Tao et al.2026 · 0 citationsarXiv
One Sample to Rule Them All: Extreme Data Efficiency in Multidiscipline Reasoning with Reinforcement Learning2601.03111v2 · Yiyuan Li, Zhen Huang, Yanan Wu et al.2026 · 0 citationsarXiv
Logics-STEM: Empowering LLM Reasoning via Failure-Driven Post-Training and Document Knowledge Enhancement2601.01562v3 · Mingyu Xu, Cheng Fang, Keyue Jiang et al.2026 · 0 citationsarXiv
Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem2512.24873v3 · Weixun Wang, XiaoXiao Xu, Wanhe An et al.2025 · 0 citationsarXiv
RollArt: Disaggregated Multi-Task Agentic RL Training at Scale2512.22560v2 · Wei Gao, Yuheng Zhao, Tianyuan Wu et al.2025 · 0 citationsarXiv
Reasoning Palette: Modulating Reasoning via Latent Contextualization for Controllable Exploration for (V)LMs2512.17206v1 · Rujiao Long, Yang Li, Xingyao Zhang et al.2025 · 0 citationsarXiv
Reconstructing KV Caches with Cross-layer Fusion For Enhanced Transformers2512.03870v3 · Hongzhan Lin, Zhiqi Bai, Xinmiao Zhang et al.2025 · 0 citationsarXiv
NEZHA: A Zero-sacrifice and Hyperspeed Decoding Architecture for Generative Recommendations2511.18793v2 · Yejing Wang, Shengyu Zhou, Jinyu Lu et al.2025 · 1 citationarXiv
BARD: budget-aware reasoning distillation2511.01470v2 · Lujie Niu, Lei Shen, Yi Jiang et al.2025 · 0 citationsarXiv
Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization2510.13554v2 · Yang Li, Zhichen Dong, Yuhan Sun et al.2025 · 0 citationsarXiv
MeSH: Memory-as-State-Highways for Recursive Transformers2510.07739v2 · Chengting Yu, Xiaobo Shu, Yadao Wang et al.2025 · 0 citationsarXiv
QAgent: A modular Search Agent with Interactive Query Understanding2510.08383v1 · Yi Jiang, Lei Shen, Lujie Niu et al.2025 · 0 citationsarXiv
How to inject knowledge efficiently? Knowledge Infusion Scaling Law for Pre-training Large Language Models2509.19371v1 · Kangtao Lv, Haibin Chen, Yujin Yuan et al.2025 · 0 citationsarXiv
DESIGNER: Design-Logic-Guided Multidisciplinary Data Synthesis for LLM Reasoning2508.12726v6 · Weize Liu, Yongchi Zhao, Yijia Luo et al.2025 · 0 citationsarXiv
Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning2508.08221v3 · Zihe Liu, Jiashun Liu, Yancheng He et al.2025 · 0 citationsarXiv
Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems2506.23090v2 · Langming Liu, Wanyu Wang, Chi Zhang et al.2025 · 4 citationsarXiv
Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library2506.06122v1 · Weixun Wang, Shaopan Xiong, Gengru Chen et al.2025 · 1 citationarXiv
Weight Spectra Induced Efficient Model Adaptation2505.23099v1 · Chongjie Si, Xuankun Yang, Muqing Liu et al.2025 · 0 citationsarXiv
Beyond Safe Answers: A Benchmark for Evaluating True Risk Awareness in Large Reasoning Models2505.19690v1 · Baihui Zheng, Boren Zheng, Kerui Cao et al.2025 · 0 citationsarXiv
USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models2505.23793v1 · Baolin Zheng, Guanlin Chen, Hongqiong Zhong et al.2025 · 1 citationarXiv
Think-J: Learning to Think for Generative LLM-as-a-Judge2505.14268v2 · Hui Huang, Yancheng He, Hongli Zhou et al.2025 · 0 citationsarXiv
ECKGBench: Benchmarking Large Language Models in E-commerce Leveraging Knowledge Graph2503.15990v1 · Langming Liu, Haibin Chen, Yuhao Wang et al.2025 · 0 citationsarXiv
Deconstructing Long Chain-of-Thought: A Structured Reasoning Optimization Framework for Long CoT Distillation2503.16385v1 · Yijia Luo, Yulin Song, Xingyao Zhang et al.2025 · 0 citationsarXiv
ChineseEcomQA: A Scalable E-commerce Concept Evaluation Benchmark for Large Language Models2502.20196v1 · Haibin Chen, Kangtao Lv, Chengwei Hu et al.2025 · 4 citationsarXiv
UQABench: Evaluating User Embedding for Prompting LLMs in Personalized Question Answering2502.19178v2 · Langming Liu, Shilei Liu, Yujin Yuan et al.2025 · 3 citationsarXiv
Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?2502.19361v3 · Yancheng He, Shilong Li, Jiaheng Liu et al.2025 · 4 citationsarXiv
AIR: Complex Instruction Generation via Automatic Iterative Refinement2502.17787v2 · Wei Liu, Yancheng He, Hui Huang et al.2025 · 1 citationarXiv
SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines2502.14739v4 · M-A-P Team, Xinrun Du, Yifan Yao et al.2025 · 5 citationsarXiv
"See the World, Discover Knowledge": A Chinese Factuality Evaluation for Large Vision Language Models2502.11718v4 · Jihao Gu, Yingyao Wang, Pi Bu et al.2025 · 0 citationsarXiv
Unlocking Scaling Law in Industrial Recommendation Systems with a Three-step Paradigm based Large User Model2502.08309v2 · Bencheng Yan, Shilei Liu, Zhiyuan Zeng et al.2025 · 2 citationsarXiv
MIM: Multi-modal Content Interest Modeling Paradigm for User Behavior Modeling2502.00321v4 · Bencheng Yan, Si Chen, Shichang Jia et al.2025 · 0 citationsarXiv
ProgCo: Program Helps Self-Correction of Large Language Models2501.01264v2 · Xiaoshuai Song, Yanan Wu, Weixun Wang et al.2025 · 1 citationarXiv
Chinese SafetyQA: A Safety Short-form Factuality Benchmark for Large Language Models2412.15265v2 · Yingshui Tan, Boren Zheng, Baihui Zheng et al.2024 · 0 citationsarXiv
Chinese SimpleQA: A Chinese Factuality Evaluation for Large Language Models2411.07140v2 · Yancheng He, Shilong Li, Jiaheng Liu et al.2024 · 9 citationsarXiv
M2rc-Eval: Massively Multilingual Repository-level Code Completion Evaluation2410.21157v1 · Jiaheng Liu, Ken Deng, Congnan Liu et al.2024 · 0 citationsarXiv
2D-DPO: Scaling Direct Preference Optimization with 2-Dimensional Supervision2410.19720v1 · Shilong Li, Yancheng He, Hui Huang et al.2024 · 1 citationarXiv
Adaptive Segment-level Reward: Bridging the Gap Between Action and Reward Space in Alignment2411.00809v3 · Yanshi Li, Shaopan Xiong, Gengru Chen et al.2024 · 0 citationsarXiv
Career total: 71 works. 58 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.