--- title: "Hua Ren Wu — papers, page 2 — Elamur Research" description: "Hua Ren Wu, North China Electric Power University: 34 papers on Elamur Research (2007–2026), h-index 52 — affiliations, topics…" canonical: "https://research.elamur.ai/free/en/authors/hua-ren-wu/page/2/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/hua-ren-wu/page/2/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Hua Ren Wu](https://md.research.elamur.ai/free/en/authors/hua-ren-wu/) / page 2 # Hua Ren Wu · page 2 34 papers in our library · 2007–2026 · page 2 of 2 [The profile, affiliations and co-authors →](https://md.research.elamur.ai/free/en/authors/hua-ren-wu/) ## Papers The most cited first (OpenAlex and our library). [← prev](https://md.research.elamur.ai/free/en/authors/hua-ren-wu/) [1](https://md.research.elamur.ai/free/en/authors/hua-ren-wu/) **2** 26. **[ERNIE-Doc: A Retrospective Long-Document Modeling Transformer](https://md.research.elamur.ai/free/en/papers/ding-2020-ernie-doc-retrospective-long/)** *(2020 · 27 citations)* Standard Transformers struggle with long documents because self-attention cost grows quadratically with input length. 27. **[ERNIE-Gram: Pre-Training with Explicitly N-Gram Masked Language Modeling for Natural Language Understanding](https://md.research.elamur.ai/free/en/papers/xiao-2020-ernie-gram-pre-training/)** *(2020 · 22 citations)* BERT-style masked language modeling learns mostly from fine-grained units, such as subwords in English or characters in Chinese. Earlier extensions mask whole spans, but they still predict each token of a span separately. This ignores how tokens inside an n-gram depend on one another and how different n-grams relate. 28. **[AttnPO: Attention-Guided Process Supervision for Efficient Reasoning](https://md.research.elamur.ai/free/en/papers/nie-2026-attnpo-attention-guided-process-supervision/)** *(2026 · 18 citations)* Reasoning models trained with RLVR tend to overthink, producing long chains of thought with little benefit. 29. **[Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking](https://md.research.elamur.ai/free/en/papers/chen-2025-inner-thinking-transformer-leveraging-dynamic/)** *(2025 · 16 citations)* Larger LLMs bring diminishing returns, and small models hit capacity limits. Chain-of-Thought style test-time scaling also has a weakness: it only works if the model produces the critical tokens correctly. The authors trained GPT-2 on AQuA and tracked gradient norms layer by layer. Tokens the model gets right settle… 30. **[DuReader_robust: A Chinese Dataset Towards Evaluating Robustness and Generalization of Machine Reading Comprehension in Real-World Applications](https://md.research.elamur.ai/free/en/papers/tang-2020-dureader-robust-chinese-dataset/)** *(2020 · 13 citations)* Neural machine reading comprehension (MRC) models often fail in real-world use. They may answer paraphrased questions inconsistently (over-sensitivity), get distracted by passage spans that share many words with the question (over-stability), or struggle outside their training domain (generalization). Earlier… 31. **[ERNIE 5.0 Technical Report](https://md.research.elamur.ai/free/en/papers/wang-2026-ernie-5-0-technical/)** *(2026 · 7 citations)* Most large multimodal systems can read images, video or audio but still answer mainly in text. When generation is added, it usually comes from separate decoders attached to a language model, which can weaken core language skills. Baidu's ERNIE 5.0 addresses this with a single autoregressive model trained from scratch… 32. **[BeamLoRA: Beam-Constraint Low-Rank Adaptation](https://md.research.elamur.ai/free/en/papers/gu-2025-beamlora-beam-constraint-low-rank/)** *(2025 · 6 citations)* Low-Rank Adaptation (LoRA) is an efficient way to fine-tune large language models, but its accuracy still has room to improve. 33. **[Reinforced Informativeness Optimization for Long-Form Retrieval-Augmented Generation](https://md.research.elamur.ai/free/en/papers/wang-2026-reinforced-informativeness-optimization-long-form/)** *(2026 · 2 citations)* Reinforcement learning has improved LLMs on math and short-answer QA, where outputs can be checked against a single correct target. 34. **[Distributional Clarity: The Hidden Driver of RL-Friendliness in Large Language Models](https://md.research.elamur.ai/free/en/papers/sun-2026-distributional-clarity-hidden-driver-rl/)** *(2026)* Under identical RL with verifiable rewards (RLVR) pipelines such as GRPO and DAPO, some model families (Qwen) improve markedly while others (Llama) gain little. [← prev](https://md.research.elamur.ai/free/en/authors/hua-ren-wu/) [1](https://md.research.elamur.ai/free/en/authors/hua-ren-wu/) **2**