Author name cluster

Dongsheng Li

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

61 papers

1 author row

EAAI Journal 2026 Journal Article

An automated framework for converting point cloud data to building information modeling with segmentation and refinement

Tianze Chen
Hongxu Wang
Dongsheng Li
Jiepeng Liu
Pengkun Liu
Zhou Wu
Chengran Xu
Meifei Zhang

Building information modeling (BIM) is important for managing buildings throughout their lifecycle. However, converting point cloud data (PCD) into BIM still depends on manual work. This study proposes a four-stage framework to improve this process. The framework includes PCD preprocessing, instance segmentation, geometric parameter estimation, and industry foundation classes (IFC) model generation. A hybrid method that combines deep learning-based semantic segmentation with unsupervised clustering is used for component recognition. A boundary and corner refinement strategy further improves model consistency. Tests on a residential dataset of 145 rooms show high accuracy, with an average element detection rate of 99. 1% and low geometric errors. The ablation study shows that model is sensitive to the choice of noise and voxel size, and the boundary and corner refinement strategy enhances the geometric accuracy and consistency. This method reduces manual effort and supports applications like renovation, facility maintenance, quality inspection, and digital twins.

Details DOI

AAAI Conference 2026 Conference Paper

Improving Long-Context Summarization with Multi-Granularity Retrieval Optimization

Xueyu Chen
Kaitao Song
Zifan Song
Dongsheng Li
Cairong Zhao

Retrieval-Augmented Generation (RAG) is an effective solution to overcome the limitations of Large Language Models (LLMs) in terms of specific-domain knowledge and timely information updates. However, current RAG methods typically respond to queries based on isolated segments, lacking the ability to integrate information within the same document. This undermines performance in real-world tasks requiring coherent understanding across an entire document. Notably, the human brain naturally integrates and summarizes prior knowledge upon reading a given text, progressively formulating a comprehensive understanding. Motivated by this cognitive process, we propose the Hierarchical Two-Stage Summarization-based Information Retrieval (HTSIR) method, which preprocesses the corpus prior to retrieval, summarizes continuous texts to obtain integrated information, and constructs a retrieval tree with varying summary granularities. The retrieved information is then processed by a Reranker based on the current question to serve as a context for LLMs. Additionally, as single-step summarization is often imprecise in query-based summarization tasks, we further apply a Refinement module, allowing LLMs to reflect and revise their output to achieve the final result. By combining HTSIR with GPT-4o mini, we achieve state-of-the-art results on complex question tasks across four long-text datasets (NarrativeQA, QASPER, QuALITY, and QMSum), achieving an improvement of about 6 points on the Question Answering (QA) task in QuALITY-HRAD.

PDF Details DOI

AAAI Conference 2026 Conference Paper

WALKSAFE: Risk-aware Graph Random Walk with Bi-GRPO for LLM Safety

Shilong Pan
Zhiliang Tian
Wanlong Yu
Zhen Huang
Qingyu Qiu
Zihan Chen
Zhonghao Sun
Minlie Huang

Large language models (LLMs) may generate harmful outputs on malicious inputs. Existing safety methods, including prompt engineering and model editing, rely on hand-crafted templates or target-driven parameter modifications, limiting their generalizability in unseen harmful scenarios. Post-training aims to ensure LLM safety in general domains via supervised fine-tuning (SFT) or reinforcement learning (RL) on diverse malicious inputs. SFT needs annotated refusal samples while RL learns to refuse risk by exploring diverse harmful inputs. However, these methods tend to harshly refuse over any possible risks, sacrificing potentially useful information and degrading model utility. We argue that realistic malicious inputs often mix both harmful and helpful semantics (i.e., entities and relations), and LLMs should identify and remove only harmful relations while preserving useful ones. Thus, the original malicious user inputs can shift into safe queries, to which LLMs can respond safely and helpfully. In this paper, we propose WALKSAFE, a graph-based risk-aware training framework that enables LLMs to identify potential risks of key semantics (entities and relations) in user inputs via graph structure. By filtering harmful relations, LLMs can respond to safe input queries and then generate their corresponding safe and helpful responses. First, we model all entities and relations in the inputs with a graph structure. Second, we adopt a risk-aware random walk on the graph to quantify potential risk under multiple entities and relations. Then, we reconstruct safe queries by filtering harmful relations to promote the LLM to answer safely and helpfully rather than with direct refusals. Finally, we propose Bi-GRPO to post-train LLMs. As vanilla GRPO conducts only the intra-group comparison, Bi-GRPO performs both intra-group and inter-group comparisons between different response groups. The extra inter-group rewards encourage the model to distinguish harmful and safe semantics, and thus prefer safe and helpful responses. Experiments on three LLMs show that our models obtain SOTA results.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Accelerating Block Coordinate Descent for LLM Finetuning via Landscape Expansion

Qijun Luo
Yifei Shen
Liangzu Peng
Dongsheng Li
Xiao Li

Finetuning large language models (LLMs) is a resource-intensive task for researchers in academia, with memory constraints posing a key bottleneck. A classic optimization method, block coordinate descent (BCD), significantly reduces memory cost by segmenting the trainable parameters into multiple blocks and optimizing one active block at a time while freezing the others. However, we identify that blindly applying BCD to train LLMs can be inefficient for two reasons. First, optimizing only the active block requires backpropagating through multiple deeper yet inactive blocks, resulting in wasteful computations. Second, the frozen blocks, when they are not quite close to optimality, can narrow the optimization landscape, potentially misguiding the training of the active block. To address these issues simultaneously, we propose integrating BCD with landscape expansion, which unfreezes the inactive blocks and updates them in a cost-efficient manner during the same backpropagation as the update to the active block. Experiments on 8B and 70B models demonstrate that our proposed method surpasses memory-efficient baselines and matches Adam's downstream performance while requiring only 24 GB of memory for the 8B model and 300 GB for the 70B model.