Chenliang Li

Writing-RL: Advancing Long-form Writing via Adaptive Curriculum Reinforcement Learning

Xuanyu Lei, Chenliang Li, Yuning Wu, Kaiming Liu et autres

Xuanyu Lei, Chenliang Li, Yuning Wu, Kaiming Liu, Weizhou Shen, Peng Li, Ming Yan, Fei Huang, Ya-Qin Zhang, Yang Liu. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

cn (code pays fourni par la source)

QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory Management

Weizhou Shen, Ziyi Yang, Chenliang Li, Zhiyuan Lu et autres

We introduce QwenLong-L1.5, a model that achieves superior long-context reasoning capabilities through systematic post-training innovations. The key technical breakthroughs of QwenLong-L1.5 are as follows: (1) Long-Context Data Synthesis Pipeline: We develop a systematic synthesis framework that generates challenging reasoning tasks requiring multi-hop …

SPELL: Self-Play Reinforcement Learning for Evolving Long-Context Language Models

Ziyi Yang, Weizhou Shen, Chenliang Li, Ruijun Chen et autres

Progress in long-context reasoning for large language models (LLMs) has lagged behind other recent advances. This gap arises not only from the intrinsic difficulty of processing long texts, but also from the scarcity of reliable human annotations and programmatically verifiable reward signals. …

Bi-VLDoc: bidirectional vision-language modeling for visually-rich document understanding

Chuwei Luo, Guozhi Tang, Qi Zheng, Cong Yao et autres

cn (code pays fourni par la source)

Token-level Preference Self-Alignment Optimization for Multi-style Outline Controllable Generation

Zihao Li, Xuekong Xu, Ziyao Chen, Lixin Zou et autres

Multi-style outline controllable generation is crucial for multiple applications, including document semantic structuring and retrievalaugmented generation.The great success of preference alignment approaches encourages their application in controllable generation tasks.However, these attempts encounter several limitations: (1) response pair requirements, (2) substantial computation costs, …

cn (code pays fourni par la source)

WritingBench: A Comprehensive Benchmark for Generative Writing

Yuning Wu, Ming Yan, Chenliang Li, Shaopeng Lai et autres

Recent advancements in large language models (LLMs) have significantly enhanced text generation capabilities, yet evaluating their performance in generative writing remains a challenge. Existing benchmarks primarily focus on generic text generation or limited in writing tasks, failing to capture the diverse requirements …

us, cn, ky (code pays fourni par la source)

mPLUG-PaperOwl: Scientific Diagram Analysis with the Multimodal Large Language Model

Anwen Hu, Yaya Shi, Haiyang Xu, Jiabo Ye et autres

Weak diagram analysis abilities of LLMs or Multimodal LLMs greatly limit their application scenarios for scientific academic paper writing. In this work, towards a more versatile copilot for academic paper writing, we mainly focus on strengthening the multi-modal diagram analysis ability of …

cn, us (code pays fourni par la source)

Efficient Sparse Attention needs Adaptive Token Release

Chaoran Zhang, Lixin Zou, Dan Luo, Min Tang et autres

In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide array of text-centric tasks. However, their `large' scale introduces significant computational and storage challenges, particularly in managing the key-value states of the transformer, which limits their wider applicability. …

Semantics-enhanced Cross-modal Masked Image Modeling for Vision-Language Pre-training

Haowei Liu, Yaya Shi, Haiyang Xu, Chunfeng Yuan et autres

In vision-language pre-training (VLP), masked image modeling (MIM) has recently been introduced for fine-grained cross-modal alignment. However, in most existing methods, the reconstruction targets for MIM lack high-level semantics, and text is not sufficiently involved in masked modeling. These two drawbacks limit …

Unifying Latent and Lexicon Representations for Effective Video-Text Retrieval

Haowei Liu, Yaya Shi, Haiyang Xu, Chunfeng Yuan et autres

In video-text retrieval, most existing methods adopt the dual-encoder architecture for fast retrieval, which employs two individual encoders to extract global latent representations for videos and texts. However, they face challenges in capturing fine-grained semantic concepts. In this work, we propose the …

Comparisons of Different Machine Learning-Based Rainfall–Runoff Simulations under Changing Environments

Chenliang Li, Ying Jiao, Guangyuan Kan, Xiaodi Fu et autres

Climate change and human activities have a great impact on the environment and have challenged the assumption of the stability of the hydrological time series and the consistency of the observed data. In order to investigate the applicability of machine learning (ML)-based …

cn (code pays fourni par la source)

Efficient Vision-and-Language Pre-training with Text-Relevant Image Patch Selection

Wei Ye, Chaoya Jiang, Haiyang Xu, Chenhao Ye et autres

Vision Transformers (ViTs) have become increasingly popular in large-scale Vision and Language Pre-training (VLP) models. Although previous VLP research has demonstrated the efficacy of ViTs, these efforts still struggle with computational inefficiencies caused by lengthy visual sequences. To address this challenge, we …