Author name cluster

Chunpu Xu

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.

4 papers

1 author row

AAAI Conference 2026 Conference Paper

SCALE: Selective Resource Allocation for Overcoming Performance Bottlenecks in Mathematical Test-time Scaling

Yang Xiao
Chunpu Xu
Ruifeng Yuan
Jessie Wang
Wenjie Li
Pengfei Liu

Test-time compute scaling has emerged as a powerful paradigm for enhancing mathematical reasoning in large language models (LLMs) by allocating additional computational resources during inference. However, current methods employ uniform resource distribution across all reasoning sub-problems, creating fundamental bottlenecks where challenging sub-problems receive insufficient attention while routine operations consume disproportionate resources. This uniform allocation creates performance bottlenecks where additional computational resources yield diminishing returns. Inspired by dual-process theory, we propose SCALE (Selective Resource Allocation), a framework that selectively allocates computational resources based on sub-problem difficulty. SCALE operates through four stages: (1) problem decomposition into sequential reasoning sub-problems, (2) difficulty assessment of each sub-problem to distinguish between routine operations and computationally challenging sub-problems, (3) selective processing mode assignment between System 1 for simple sub-problems and System 2 for complex ones, and (4) sequential execution with context propagation. By concentrating resources on challenging sub-problems while processing routine operations efficiently, SCALE achieves substantial performance improvements with superior resource utilization. Extensive experiments demonstrate that SCALE significantly outperforms uniform scaling baselines, achieving accuracy improvements of up to 13.75 percentage points (57.50% to 71.25% on AIME25) while reducing computational costs by 33-53%, representing a major advance in test-time scaling that addresses fundamental limitations of current approaches.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

LIMOPro: Reasoning Refinement for Efficient and Effective Test-time Scaling

Yang Xiao
Jiashuo WANG
Ruifeng Yuan
Chunpu Xu
Kaishuai Xu
Wenjie Li
Pengfei Liu

Large language models (LLMs) have demonstrated remarkable reasoning capabilities through test-time scaling approaches, particularly when fine-tuned with chain-of-thought (CoT) data distilled from more powerful large reasoning models (LRMs). However, these reasoning chains often contain verbose elements that mirror human problem-solving, categorized as progressive reasoning (the essential solution development path) and functional elements (verification processes, alternative solution approaches, and error corrections). While progressive reasoning is crucial, the functional elements significantly increase computational demands during test-time inference. We introduce PIR (Perplexity-based Importance Refinement), a principled framework that quantitatively evaluates the importance of each reasoning step based on its impact on answer prediction confidence. PIR systematically identifies and selectively prunes only low-importance functional steps while preserving all progressive reasoning components, creating optimized training data that maintains the integrity of the core solution path while reducing verbosity. Models fine-tuned on PIR-optimized data exhibit superior test-time scaling properties, generating more concise reasoning chains while achieving improved accuracy (+0. 9\% to +6. 6\%) with significantly reduced token usage (-3\% to -41\%) across challenging reasoning benchmarks (AIME, AMC, and GPQA Diamond). Our approach demonstrates strong generalizability across different model sizes, data sources, and token budgets, offering a practical solution for deploying reasoning-capable LLMs in scenarios where efficient test-time scaling, response time, and computational efficiency are valuable constraints. Code and dataset are available at the LIMOPro GitHub repository.

PDF Details

AAAI Conference 2021 Conference Paper

Imagine, Reason and Write: Visual Storytelling with Graph Knowledge and Relational Reasoning

Chunpu Xu
Min Yang
Chengming Li
Ying Shen
Xiang Ao
Ruifeng Xu

Visual storytelling is the task of generating a short story to describe an ordered image stream. Different from visual captions, stories contain not only factual descriptions, but also imaginary concepts that do not appear in the images. In this paper, we propose a novel imagine-reason-write generation framework (IRW) for visual storytelling, inspired by the logic of humans when they write a story. First, a multimodal imagining module is leveraged to learn the imaginative storyline explicitly, improving the coherence and reasonability of the generated story. Second, we employ a relational reasoning module to fully exploit the external knowledge (commonsense knowledge base) and task-specific knowledge (scene graph and event graph) with a relational reasoning method based on the storyline. In this way, we can effectively capture the most informative commonsense and visual relationships among objects in images, enhancing the diversity and informativeness of the generated story. Finally, we integrate the visual information and semantic (concept) information to generate human-like stories. Extensive experiments on a benchmark dataset (i. e. , VIST) demonstrate that the proposed IRW framework substantially outperforms the state-of-the-art methods across multiple evaluation metrics.

PDF Details

AAAI Conference 2020 Conference Paper

Interactive Dual Generative Adversarial Networks for Image Captioning

Junhao Liu
Kai Wang
Chunpu Xu
Zhou Zhao
Ruifeng Xu
Ying Shen
Min Yang

Image captioning is usually built on either generationbased or retrieval-based approaches. Both ways have certain strengths but suffer from their own limitations. In this paper, we propose an Interactive Dual Generative Adversarial Network (IDGAN) for image captioning, which mutually combines the retrieval-based and generation-based methods to learn a better image captioning ensemble. IDGAN consists of two generators and two discriminators, where the generation- and retrieval-based generators mutually beneﬁt from each other’s complementary targets that are learned from two dual adversarial discriminators. Speciﬁcally, the generation- and retrieval-based generators provide improved synthetic and retrieved candidate captions with informative feedback signals from the two respective discriminators that are trained to distinguish the generated captions from the true captions and assign top rankings to true captions respectively, thus featuring the merits of both retrieval-based and generation-based approaches. Extensive experiments on MSCOCO dataset demonstrate that the proposed IDGAN model signiﬁcantly outperforms the compared methods for image captioning.

PDF Details