Author

Yunfang Wu

Observed name: Wu, Yunfang

Institution: Peking University

Observed institution: Peking University

OpenAlex ID: A5140870728

Learning Latent Reasoning Traces for Scalar Reward Models End-to-End

2026 · Lee, Sanwoo, Bai, Clive, et al. · arXiv (Cornell University)

PDF

Safety-Utility Conflicts Are Not Global: Surgical Alignment via Head-Level Diagnosis

2026 · Association for Computational Linguistics 2026, Bao, Chenfu, et al. · Underline Science Inc.

Do Not Step Into the Same River Twice: Learning to Reason from Trial and Error

2026 · Association for Computational Linguistics 2026, Bai, Clive, et al. · Underline Science Inc.

Aligning Language Models with Real-time Knowledge Editing

2026 · Association for Computational Linguistics 2026, Tang, Chenming, et al. · Underline Science Inc.

Think Outside the Policy: In-Context Steered Policy Optimization

2026 · Association for Computational Linguistics 2026, Bai, Clive, et al. · Underline Science Inc.

RLVR Datasets and Where to Find Them: Tracing Data Lineage for Better Training Data

2026 · Huang, Hsiu-Yuan, Liu, Weijie, et al. · arXiv (Cornell University)

PDF

RepoZero: Can LLMs Generate a Code Repository from Scratch?

2026 · Zhang, Zhaoxi, Xu, Yiming, et al. · arXiv (Cornell University)

PDF

Not All Tokens Learn Alike: Attention Entropy Reveals Heterogeneous Signals in RL Reasoning

2026 · Li, Gengyang, Wu, Zheng-Fan, et al. · arXiv (Cornell University)

PDF

SyncThink: A Training-Free Strategy to Align Inference Termination with Reasoning Saturation

2026 · Li, Gengyang, Cai, Wang, et al. · arXiv (Cornell University)

PDF

Aligning Language Models with Real-time Knowledge Editing

2026 · Chenming Tang, Yutong Yang, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting

PDF

ORBIT: On-policy Exploration-Exploitation for Controllable Multi-Budget Reasoning

2026 · Kun Liang, Clive Bai, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)

PDF

Securing the Floor and Raising the Ceiling: A Merging-based Paradigm for Multi-modal Search Agents

2026 · Zhixiang Wang, Jingxuan Xu, et al. · Workshop for Research on Agent Language Models (REALM)

PDF

Trait-Aware Policy Optimization for Autoregressive Multi-Trait Essay Scoring

2026 · Zhengyang Wang, Sanwoo Lee, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)

PDF

ActTraitBench: Quantifying the Knowledge-Decision Gap in Large Language Models via Human-Grounded Behavioral Validation

2026 · Yutong Yang, Chenxi Miao, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)

PDF

A Unified Framework to Elicit Structured Feedback for Interpretable Multi-Trait Essay Scoring

2026 · Shihang Yang, Sanwoo Lee, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)

PDF

Works count: 15

Citation count:

H-index:

I10-index: