Xingjian Diao

34 papers A* 3A 1B 1Journal 20Unranked 9
YearRankTypeTitle / Venue / Authors
2026 J jnl
Addressing Overthinking in Large Vision-Language Models via Gated Perception-Reasoning Optimization.
CoRR
Xingjian Diao, Zheyuan Liu, Chunhui Zhang, Weiyi Wu, Keyi Kong, Lin Shi, Kaize Ding, Soroush Vosoughi, Jiang Gui
2026 J jnl
Exploiting Label-Independent Regularization from Spatial Dependencies for Whole Slide Image Analysis.
CoRR
Weiyi Wu, Xinwen Xu, Chongyang Gao, Xingjian Diao, Siting Li, Jiang Gui
2026 — conf
Tailoring Memory Granularity for Multi-Hop Reasoning over Long Contexts.
EACL (Findings)
Peijun Qing, Xingjian Diao, Chiyu Ma, Saeed Hassanpour, Soroush Vosoughi
2025 — conf
Assessing and Mitigating Medical Knowledge Drift and Conflicts in Large Language Models.
EMNLP (Findings)
Weiyi Wu, Xinwen Xu, Chongyang Gao, Xingjian Diao, Siting Li, Lucas A. Salas, Jiang Gui
2025 J jnl
Assessing and Mitigating Medical Knowledge Drift and Conflicts in Large Language Models.
CoRR
Weiyi Wu, Xinwen Xu, Chongyang Gao, Xingjian Diao, Siting Li, Lucas A. Salas, Jiang Gui
2025 A conf
FT2TF: First-Person Statement Text-to-Talking Face Generation.
WACV
Xingjian Diao, Ming Cheng, Wayner Barrios, SouYoung Jin
2025 — conf
Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge.
IJCNLP-AACL (long papers)
Lin Shi, Chiyu Ma, Wenhua Liang, Xingjian Diao, Weicheng Ma, Soroush Vosoughi
2025 — conf
Knowing More, Acting Better: Hierarchical Representation for Embodied Decision-Making.
EMNLP (Findings)
Chunhui Zhang, Zhongyu Ouyang, Xingjian Diao, Zheyuan Liu, Soroush Vosoughi
2025 J jnl
Learning Musical Representations for Music Performance Question Answering.
CoRR
Xingjian Diao, Chunhui Zhang, Tingxuan Wu, Ming Cheng, Zhongyu Ouyang, Weiyi Wu, Jiang Gui
2025 — conf
Learning Sparsity for Effective and Efficient Music Performance Question Answering.
ACL (2)
Xingjian Diao, Tianzhen Yang, Chunhui Zhang, Weiyi Wu, Ming Cheng, Jiang Gui
2025 J jnl
Learning Sparsity for Effective and Efficient Music Performance Question Answering.
CoRR
Xingjian Diao, Tianzhen Yang, Chunhui Zhang, Weiyi Wu, Ming Cheng, Jiang Gui
2025 J jnl
Music's Multimodal Complexity in AVQA: Why We Need More than General Multimodal LLMs.
CoRR
Wenhao You, Xingjian Diao, Chunhui Zhang, Keyi Kong, Weiyi Wu, Zhongyu Ouyang, Chiyu Ma, Tingxuan Wu, Noah Wei, Zong Ke, Ming Cheng, Soroush Vosoughi, Jiang Gui
2025 A* conf
ProtoVQA: An Adaptable Prototypical Framework for Explainable Fine-Grained Visual Question Answering.
EMNLP
Xingjian Diao, Weiyi Wu, Keyi Kong, Peijun Qing, Xinwen Xu, Ming Cheng, Soroush Vosoughi, Jiang Gui
2025 J jnl
ProtoVQA: An Adaptable Prototypical Framework for Explainable Fine-Grained Visual Question Answering.
CoRR
Xingjian Diao, Weiyi Wu, Keyi Kong, Peijun Qing, Xinwen Xu, Ming Cheng, Soroush Vosoughi, Jiang Gui
2025 A* conf
SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models.
EMNLP
Xingjian Diao, Chunhui Zhang, Keyi Kong, Weiyi Wu, Chiyu Ma, Zhongyu Ouyang, Peijun Qing, Soroush Vosoughi, Jiang Gui
2025 J jnl
SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models.
CoRR
Xingjian Diao, Chunhui Zhang, Keyi Kong, Weiyi Wu, Chiyu Ma, Zhongyu Ouyang, Peijun Qing, Soroush Vosoughi, Jiang Gui
2025 — conf
Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding.
NAACL (Findings)
Xingjian Diao, Chunhui Zhang, Weiyi Wu, Zhongyu Ouyang, Peijun Qing, Ming Cheng, Soroush Vosoughi, Jiang Gui
2025 J jnl
Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding.
CoRR
Xingjian Diao, Chunhui Zhang, Weiyi Wu, Zhongyu Ouyang, Peijun Qing, Ming Cheng, Soroush Vosoughi, Jiang Gui
2025 J jnl
What Makes a Good Curriculum? Disentangling the Effects of Data Ordering on LLM Mathematical Reasoning.
CoRR
Yaning Jia, Chunhui Zhang, Xingjian Diao, Xiangchi Yuan, Zhongyu Ouyang, Chiyu Ma, Soroush Vosoughi
2024 A* conf
AlphaLoRA: Assigning LoRA Experts Based on Layer Training Quality.
EMNLP
Peijun Qing, Chongyang Gao, Yefan Zhou, Xingjian Diao, Yaoqing Yang, Soroush Vosoughi
2024 J jnl
AlphaLoRA: Assigning LoRA Experts Based on Layer Training Quality.
CoRR
Peijun Qing, Chongyang Gao, Yefan Zhou, Xingjian Diao, Yaoqing Yang, Soroush Vosoughi
2024 J jnl
CrossGP: Cross-Day Glucose Prediction Excluding Physiological Information.
CoRR
Ziyi Zhou, Ming Cheng, Yanjun Cui, Xingjian Diao, Zhaorui Ma
2024 — conf
Efflex: Efficient and Flexible Pipeline for Spatio-Temporal Trajectory Graph Modeling and Representation Learning.
CVPR Workshops
Ming Cheng, Ziyi Zhou, Bowen Zhang, Ziyu Wang, Jiaqi Gan, Ziang Ren, Weiqi Feng, Yi Lyu, Hefan Zhang, Xingjian Diao
2024 J jnl
Efflex: Efficient and Flexible Pipeline for Spatio-Temporal Trajectory Graph Modeling and Representation Learning.
CoRR
Ming Cheng, Ziyi Zhou, Bowen Zhang, Ziyu Wang, Jiaqi Gan, Ziang Ren, Weiqi Feng, Yi Lyu, Hefan Zhang, Xingjian Diao
2024 — conf
GluMarker: A Novel Predictive Modeling of Glycemic Control Through Digital Biomarkers.
EMBC
Ziyi Zhou, Ming Cheng, Xingjian Diao, Yanjun Cui, Xiangling Li
2024 J jnl
GluMarker: A Novel Predictive Modeling of Glycemic Control Through Digital Biomarkers.
CoRR
Ziyi Zhou, Ming Cheng, Xingjian Diao, Yanjun Cui, Xiangling Li
2024 — conf
Learning Musical Representations for Music Performance Question Answering.
EMNLP (Findings)
Xingjian Diao, Chunhui Zhang, Tingxuan Wu, Ming Cheng, Zhongyu Ouyang, Weiyi Wu, Jiang Gui
2024 J jnl
Toward Short-Term Glucose Prediction Solely Based on CGM Time Series.
CoRR
Ming Cheng, Xingjian Diao, Ziyi Zhou, Yanjun Cui, Wenjun Liu, Shitong Cheng
2024 J jnl
VeTraSS: Vehicle Trajectory Similarity Search Through Graph Modeling and Representation Learning.
CoRR
Ming Cheng, Bowen Zhang, Ziyu Wang, Ziyi Zhou, Weiqi Feng, Yi Lyu, Xingjian Diao
2023 B conf
AV-MaskEnhancer: Enhancing Video Representations through Audio-Visual Masked Autoencoder.
ICTAI
Xingjian Diao, Ming Cheng, Shitong Cheng
2023 J jnl
AV-MaskEnhancer: Enhancing Video Representations through Audio-Visual Masked Autoencoder.
CoRR
Xingjian Diao, Ming Cheng, Shitong Cheng
2023 J jnl
An End-to-End Energy-Efficient Approach for Intake Detection With Low Inference Time Using Wrist-Worn Sensor.
IEEE J. Biomed. Health Informatics
Boyang Wei, Shibo Zhang, Xingjian Diao, Qiuyang Xu, Yang Gao, Nabil Alshurafa
2023 J jnl
FT2TF: First-Person Statement Text-To-Talking Face Generation.
CoRR
Xingjian Diao, Ming Cheng, Wayner Barrios, SouYoung Jin
2023 J jnl
SAIC: Integration of Speech Anonymization and Identity Classification.
CoRR
Ming Cheng, Xingjian Diao, Shitong Cheng, Wenjun Liu