publications

2026

1. arXiv

   Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning

   Shaotian Yan, Kaiyuan Liu, Chen Shen^*, Bing Wang, Sinan Fan, Jun Zhang, Yue Wu, and 2 more authors

   arXiv preprint arXiv:2601.09088, 2026

   arXiv Code
2. ICLR

   Where Did This Sentence Come From? Tracing Provenance in LLM Reasoning Distillation

   Kaiyuan Liu, Shaotian Yan, Rui Miao, Bing Wang, Chen Shen^*, Jun Zhang, and Jieping Ye

   ICLR 2026, arXiv preprint arXiv:2512.20908, 2026

   arXiv
3. ICLR Oral

   Hallucination Begins Where Saliency Drops

   Xiaofeng Zhang, Yuanchao Zhu, Chaochen Gu, Xiaosong Yuan, Qiyan Zhao, Jiawei Cao, Feilong Tang, and 4 more authors

   ICLR 2026 Oral, arXiv preprint arXiv:2601.20279, 2026

   arXiv
4. ICLR

   Differential Fine-Tuning Large Language Models Towards Better Diverse Reasoning Abilities

   Xiaosong Yuan, Chen Shen^*, Shaotian Yan, Kaiyuan Liu, Xiaofeng Zhang, Liang Xie, Wenxiao Wang, and 3 more authors

   ICLR, 2026

2025

1. ACL

   Enhancing Chain-of-Thought Reasoning with Critical Representation Fine-tuning

   Chenxi Huang, Shaotian Yan, Liang Xie, Binbin Lin, Sinan Fan, Yue Xin, Deng Cai, and 2 more authors

   In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

   arXiv
2. EMNLP

   Shallow Focus, Deep Fixes: Enhancing Shallow Layers Vision Attention Sinks to Alleviate Hallucination in LVLMs

   Xiaofeng Zhang, Yihao Quan, Chen Shen^*, Chaochen Gu, Xiaosong Yuan, Shaotian Yan, Jiawei Cao, and 3 more authors

   In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025
3. EMNLP

   SalaMAnder: Shapley-based Mathematical Expression Attribution and Metric for Chain-of-Thought Reasoning

   Yue Xin, Chen Shen^*, Shaotian Yan, Xiaosong Yuan, Yaoming Wang, Xiaofeng Zhang, Chenxi Huang, and 1 more author

   EMNLP 2025, arXiv preprint arXiv:2509.16561, 2025

   arXiv
4. NeurIPS

   GeoCAD: Local Geometry-Controllable CAD Generation with Large Language Models

   Zhanwei Zhang, Junjie Liu, Wenxiao Wang, Binbin Lin, Liang Xie, Chen Shen, and Deng Cai

   In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025
5. arXiv

   Enhancing Large Language Models with Reward-guided Tree Search for Knowledge Graph Question and Answering

   Xiao Long, Liansheng Zhuang, Chen Shen, Shaotian Yan, Yifei Li, and Shafei Wang

   arXiv preprint arXiv:2505.12476, 2025

   arXiv
6. arXiv

   Efficient Reasoning through Suppression of Self-affirmation Reflections in Large Reasoning Models

   Kaiyuan Liu, Chen Shen^*, Zhanwei Zhang, Junjie Liu, Xiaosong Yuan, and others

   arXiv preprint arXiv:2506.12353, 2025

   arXiv
7. ICLR

   Don’t Take Things Out of Context: Attention Intervention for Enhancing Chain-of-Thought Reasoning in Large Language Models

   Shaotian Yan, Chen Shen^*, Wenxiao Wang, Liang Xie, Junjie Liu, and Jieping Ye

   In The Thirteenth International Conference on Learning Representations, 2025

   Abs arXiv

   Few-shot Chain-of-Thought (CoT) significantly enhances the reasoning capabilities of large language models (LLMs), functioning as a whole to guide these models in generating reasoning steps toward final answers. However, we observe that isolated segments, words, or tokens within CoT demonstrations can unexpectedly disrupt the generation process of LLMs. The model may overly concentrate on certain local information present in the demonstration, introducing irrelevant noise into the reasoning process and potentially leading to incorrect answers. In this paper, we investigate the underlying mechanism of CoT through dynamically tracing and manipulating the inner workings of LLMs at each output step, which demonstrates that tokens exhibiting specific attention characteristics are more likely to induce the model to take things out of context; these tokens directly attend to the hidden states tied with prediction, without substantial integration of non-local information. Building upon these insights, we propose a Few-shot Attention Intervention method (FAI) that dynamically analyzes the attention patterns of demonstrations to accurately identify these tokens and subsequently make targeted adjustments to the attention weights to effectively suppress their distracting effect on LLMs. Comprehensive experiments across multiple benchmarks demonstrate consistent improvements over baseline methods, with a remarkable 5.91% improvement on the AQuA dataset, further highlighting the effectiveness of FAI.

8. ICLR

   Improving Complex Reasoning with Dynamic Prompt Corruption: A Soft Prompt Optimization Approach

   Sinan Fan, Liang Xie, Chen Shen^*, Ge Teng, Xiaosong Yuan, Xiaofeng Zhang, Chenxi Huang, and 3 more authors

   In The Thirteenth International Conference on Learning Representations, 2025

   arXiv Poster

2024

1. Neupl

   Large-Scale Clustering on 100 M-Scale Datasets Using a Single T4 GPU via Recall KNN and Subgraph Segmentation

   Junjie Liu, Rongxin Jiang, Xuesong Liu, Fan Zhou, Yaowu Chen, and Chen Shen^*

   Neural Processing Letters, 2024
2. ICML

   A3S: A General Active Clustering Method with Pairwise Constraints

   Xun Deng, Junlong Liu, Han Zhong, Fuli Feng, Chen Shen, Xiangnan He, Jieping Ye, and 1 more author

   In ICML 2024, Forty-first International Conference on Machine Learning, 2024
3. arXiv

   SciPIP: An LLM-based Scientific Paper Idea Proposer

   Wenxiao Wang, Lihui Gu, Liye Zhang, Yunxiang Luo, Yi Dai, Chen Shen, Liang Xie, and 3 more authors

   arXiv preprint arXiv:2410.23166, 2024

   arXiv
4. KDD

   URRL-IMVC: Unified and Robust Representation Learning for Incomplete Multi-view Clustering

   Ge Teng, Ting Mao, Chen Shen^*, Xiang Tian, Xuesong Liu, Yaowu Chen, and Jieping Ye

   In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2024
5. TKDE

   Self-learning Symmetric Multi-view Probabilistic Clustering

   Junjie Liu, Junlong Liu, Rongxin Jiang, Yaowu Chen, Chen Shen^*, and Jieping Ye

   IEEE Transactions on Knowledge and Data Engineering, 2024
6. NeurIPS

   Instance-adaptive Zero-shot Chain-of-Thought Prompting

   Xiaosong Yuan, Chen Shen^*, Shaotian Yan, Xiaofeng Zhang, Liang Xie, Wenxiao Wang, Renchu Guan, and 2 more authors

   In Advances in Neural Information Processing Systems, 2024

   arXiv

2022

1. CVPR

   MPC: Multi-view Probabilistic Clustering

   Junjie Liu, Junlong Liu, Shaotian Yan, Rongxin Jiang, Xiang Tian, Boxuan Gu, Yaowu Chen, and 2 more authors

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
2. ECCV

   On Mitigating Hard Clusters for Face Clustering

   Yingjie Chen, Huasong Zhong, Chong Chen, Chen Shen, Jianqiang Huang, Tao Wang, Yun Liang, and 1 more author

   In European Conference on Computer Vision, 2022
3. ACSSens

   Visual-Olfactory Synergistic Perception Based on Dual-focus Imaging and a Bionic Learning Architecture

   Yaoxuan Cui, Xubin Zheng, Chen Shen, Libin Qian, Hao Dong, Qingjun Liu, Xing Chen, and 3 more authors

   ACS sensors, 2022

2020

1. TMM

   Self-adaptive Neural Module Transformer for Visual Question Answering

   Huasong Zhong, Jingyuan Chen, Chen Shen, Hanwang Zhang, Jianqiang Huang, and Xian-Sheng Hua

   IEEE Transactions on Multimedia, 2020
2. ACM MM

   PCPL: Predicate-correlation Perception Learning for Unbiased Scene Graph Generation

   Shaotian Yan, Chen Shen^*, Zhongming Jin, Jianqiang Huang, Rongxin Jiang, Yaowu Chen, and Xian-Sheng Hua

   In Proceedings of the 28th ACM international conference on multimedia, 2020

2019

1. TOMM

   Multi-level Similarity Perception Network for Person Re-identification

   Chen Shen, Zhongming Jin, Wenqing Chu, Rongxin Jiang, Yaowu Chen, Guo-Jun Qi, and Xian-Sheng Hua

   ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2019

2018

1. TCSVT

   Sharp Attention Network via Adaptive Sampling for Person Re-identification

   Chen Shen, Guo-Jun Qi, Rongxin Jiang, Zhongming Jin, Hongwei Yong, Yaowu Chen, and Xian-Sheng Hua

   IEEE Transactions on Circuits and Systems for Video Technology, 2018
2. ACM MM

   Previewer for Multi-scale Object Detector

   Zhihang Fu, Zhongming Jin, Guo-Jun Qi, Chen Shen, Rongxin Jiang, Yaowu Chen, and Xian-Sheng Hua

   In Proceedings of the 26th ACM international conference on Multimedia, 2018

2017

1. TIP

   Multi-task Vehicle Detection with Region-of-Interest Voting

   Wenqing Chu, Yao Liu, Chen Shen, Deng Cai, and Xian-Sheng Hua

   IEEE Transactions on Image Processing, 2017
2. ACM MM

   Learning Feature Embedding with Strong Neural Activations for Fine-grained Retrieval

   Chen Shen, Chang Zhou, Zhongming Jin, Wenqing Chu, Rongxin Jiang, Yaowu Chen, and Xian-Sheng Hua

   In Proceedings of the on Thematic Workshops of ACM Multimedia 2017, 2017
3. ACM MM

   Spatio-temporal Autoencoder for Video Anomaly Detection

   Yiru Zhao, Bing Deng, Chen Shen, Yao Liu, Hongtao Lu, and Xian-Sheng Hua

   In Proceedings of the 25th ACM international conference on Multimedia, 2017
4. ACM MM

   Deep Siamese Network with Multi-level Similarity Perception for Person Re-identification

   Chen Shen, Zhongming Jin, Yiru Zhao, Zhihang Fu, Rongxin Jiang, Yaowu Chen, and Xian-Sheng Hua

   In Proceedings of the 25th ACM international conference on Multimedia, 2017