6 citations · 16 across the 23 of their papers we have counts for
27 papers
Seeing, Maintaining, and Learning: The Evolution of Multimodal Agent Memory
Minghao Guo, Qingyue Jiao, Xiujin Liu +77
Multimodal models and agents have emerged to enable AI systems to learn from and interact with the real world more like humans by integrating information across multiple modalities…
Of Errors and Echoes: Responsibility-Aware Credit Assignment for Tool-Use Agents
Xingjian Diao, Tianyu Yang, Wenjun Huang +8
Reinforcement learning improves tool-use agents, yet fine-grained credit assignment remains challenging even with step-level feedback. An observed error may be inherited from an ea…
ADAPT: Audio-Depth Action Planning with Transition-Aware Rewards for Lights-Out Industrial Navigation
Wenjun Huang, Shenghao Fu, Yian Jin +12
Vision-language-action models for embodied navigation typically rely on RGB observations, limiting their applicability in lights-out industrial environments where visible illuminat…
Which Tokens Should SFT Actually Learn? A Token-Trimming Perspective on Mathematical Reasoning
Yaning Jia, Chunhui Zhang, Wenxuan Xu +3
Supervised fine-tuning (SFT) applies a uniform cross-entropy loss to all target tokens, even though different tokens provide unequal learning signals for mathematical reasoning. Th…
HiST: A Hierarchical Sparse Transformer for Cross-Modal Spatial Transcriptomics Modeling
Weiyi Wu, Xinwen Xu, Xingjian Diao +4
Spatial transcriptomics (ST) links gene expression with tissue morphology but remains expensive and low-throughput, motivating surrogates that infer expression from routine histolo…
Doc-to-Atom: Learning to Compile and Compose Memory Atoms
Xingjian Diao, Wenbo Li, Yashas Malur Saidutta +3
Long input sequences are central to document understanding and multi-step reasoning in Large Language Models, yet the quadratic cost of attention makes inference both memory-intens…
Exploiting Label-Independent Regularization from Spatial Dependencies for Whole Slide Image Analysis
Weiyi Wu, Xinwen Xu, Chongyang Gao +3
Whole slide images, with their gigapixel-scale panoramas of tissue samples, are pivotal for precise disease diagnosis. However, their analysis is hindered by immense data size and…
Addressing Overthinking in Large Vision-Language Models via Gated Perception-Reasoning Optimization
Xingjian Diao, Zheyuan Liu, Chunhui Zhang +6
Large Vision-Language Models (LVLMs) have exhibited strong reasoning capabilities through chain-of-thought mechanisms that generate step-by-step rationales. However, such slow-thin…
What Makes a Good Curriculum? Disentangling the Effects of Data Ordering on LLM Mathematical Reasoning
Yaning Jia, Chunhui Zhang, Xingjian Diao +4
Curriculum learning (CL) - ordering training data from easy to hard - has become a popular strategy for improving reasoning in large language models (LLMs). Yet prior work employs…
ProtoVQA: An Adaptable Prototypical Framework for Explainable Fine-Grained Visual Question Answering
Xingjian Diao, Weiyi Wu, Keyi Kong +5
Visual Question Answering (VQA) is increasingly used in diverse applications ranging from general visual reasoning to safety-critical domains such as medical imaging and autonomous…
Learning Sparsity for Effective and Efficient Music Performance Question Answering
Xingjian Diao, Tianzhen Yang, Chunhui Zhang +3
Music performances, characterized by dense and continuous audio as well as seamless audio-visual integration, present unique challenges for multimodal scene understanding and reaso…
SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models
Xingjian Diao, Chunhui Zhang, Keyi Kong +6
While large language models have demonstrated impressive reasoning abilities, their extension to the audio modality, particularly within large audio-language models (LALMs), remain…
Music Audio-Visual Question Answering Requires Specialized Multimodal Designs
Wenhao You, Xingjian Diao, Wenjun Huang +9
While recent Multimodal Large Language Models exhibit impressive capabilities for general multimodal tasks, specialized domains like music necessitate tailored approaches. Music Au…
Assessing and Mitigating Medical Knowledge Drift and Conflicts in Large Language Models
Weiyi Wu, Xinwen Xu, Chongyang Gao +4
Large Language Models (LLMs) have great potential in the field of health care, yet they face great challenges in adapting to rapidly evolving medical knowledge. This can lead to ou…
Learning Musical Representations for Music Performance Question Answering
Xingjian Diao, Chunhui Zhang, Tingxuan Wu +4
Music performances are representative scenarios for audio-visual modeling. Unlike common scenarios with sparse audio, music performances continuously involve dense audio signals th…
Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding
Xingjian Diao, Chunhui Zhang, Weiyi Wu +5
Multimodal foundation models (MFMs) have demonstrated significant success in tasks such as visual captioning, question answering, and image-text retrieval. However, these models fa…
AlphaLoRA: Assigning LoRA Experts Based on Layer Training Quality
Peijun Qing, Chongyang Gao, Yefan Zhou +3
Parameter-efficient fine-tuning methods, such as Low-Rank Adaptation (LoRA), are known to enhance training efficiency in Large Language Models (LLMs). Due to the limited parameters…
Learning Spatial-Preserving Hierarchical Representations for Digital Pathology
Weiyi Wu, Xingjian Diao, Chunhui Zhang +4
Whole slide images (WSIs) pose fundamental computational challenges due to their gigapixel resolution and the sparse distribution of informative regions. Existing approaches often…
Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge
Lin Shi, Chiyu Ma, Wenhua Liang +3
LLM-as-a-Judge has emerged as a promising alternative to human evaluators across various tasks, yet inherent biases - particularly position bias, the tendency to favor solutions ba…
GluMarker: A Novel Predictive Modeling of Glycemic Control Through Digital Biomarkers
Ziyi Zhou, Ming Cheng, Xingjian Diao +2
The escalating prevalence of diabetes globally underscores the need for diabetes management. Recent research highlights the growing focus on digital biomarkers in diabetes manageme…
Toward Short-Term Glucose Prediction Solely Based on CGM Time Series
Ming Cheng, Xingjian Diao, Ziyi Zhou +3
The global diabetes epidemic highlights the importance of maintaining good glycemic control. Glucose prediction is a fundamental aspect of diabetes management, facilitating real-ti…
CrossGP: Cross-Day Glucose Prediction Excluding Physiological Information
Ziyi Zhou, Ming Cheng, Yanjun Cui +2
The increasing number of diabetic patients is a serious issue in society today, which has significant negative impacts on people's health and the country's financial expenditures.…
Efflex: Efficient and Flexible Pipeline for Spatio-Temporal Trajectory Graph Modeling and Representation Learning
Ming Cheng, Ziyi Zhou, Bowen Zhang +7
In the landscape of spatio-temporal data analytics, effective trajectory representation learning is paramount. To bridge the gap of learning accurate representations with efficient…
VeTraSS: Vehicle Trajectory Similarity Search Through Graph Modeling and Representation Learning
Ming Cheng, Bowen Zhang, Ziyu Wang +4
Trajectory similarity search plays an essential role in autonomous driving, as it enables vehicles to analyze the information and characteristics of different trajectories to make…