YLYan Liu

Yan Liu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Yan Liu has a total of 204 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Alignment in Multimodal Large Language Models: A Survey

    by Yuyao Yang, Jiaxing Zhang, Ling Yue, Linsey Pang, Zhiwei Liu, Zixian Ma, Zheng Zhao, Jialiang Yin, Mingdai Yang, Huayi Yang, et al.

    Multimodal large language models (MLLMs) can generate fluent responses but may overlook relevant evidence or violate task and safety constraints. This survey examines MLLM alignment through two complementary gaps: the Modality Gap, concerning cross-modal correspondence and the use of task-relevant evidence, and the Intent Gap, concerning behavior relative to specified goals, constraints, and human expectations. We organize the literature along six dimensions: architecture, objective functions, data construction, training, evaluation, and applications. Across these dimensions, we link alignment mechanisms and supervision assumptions to the failures they target and the evidence supporting their effectiveness. Our analysis clarifies what interface compatibility, target imitation, preference learning, and verifiable rewards can each demonstrate about alignment, together with the limitations of their underlying supervision. We further summarize evaluation at the representation, task, and behavior levels, emphasizing evidence dependence, constraint compliance, and the distinction between observed improvements and explanations of their underlying mechanisms. Applications in robotics, safety, healthcare, recommendation, and climate decision support reveal three recurring requirements: traceable evidence, valid supervision, and decisions that respect domain constraints. Building on this synthesis, we identify four research directions: evidence-consistent alignment across modalities, verified self-correction and test-time alignment, diagnosis-guided repair, and reliable transfer to underrepresented settings.

  • Open Access

    The Second Workshop on SciSoc Agents & LLMs: Agentic AI for Scientific and Societal Advances

    by Jiayuan Ding, Wei Jin, Carl Yang, Yixin Wang, Chanyoung Park, Xiangliang Zhang, Jimeng Sun, Danai Koutra, B. Aditya Prakash, Yan Liu

    The Second Workshop on SciSoc Agents & LLMs: Agentic AI for Scientific and Societal Advances aims to explore the emerging paradigm of agentic artificial intelligence, where Large Language Models (LLMs) are combined with autonomous agents, tools, memory, and multi-step reasoning to drive scientific discovery and address critical societal challenges. As LLMs continue to advance in capability, their integration into agent-based systems enables more interactive, goal-driven, and adaptive workflows that go beyond passive text generation. In particular, Agentic AI systems have demonstrated strong potential in orchestrating complex scientific pipelines, reasoning over large and heterogeneous datasets, interacting with external environments, and supporting decision-making in domains such as healthcare, environmental science, education, public policy, and social sciences. By bringing together researchers and practitioners from AI, data mining, science, and society, this workshop aims to foster a comprehensive understanding of how LLMs and agent-based architectures jointly redefine traditional research methodologies. Participants will explore novel agentic frameworks, multi-agent collaboration, and real-world deployments that leverage LLM-powered agents to accelerate scientific progress and generate meaningful societal impact.

  • Open Access

    GLACIER: A Multimodal Student-Teacher Foundation Model for Molecular Property Prediction

    by Emily Nguyen, Yongchan Hong, Harsh Toshniwal, Yan Liu, Andreas Luttens

    Deep learning models facilitate the discovery of molecules with tailored properties among billions of candidate compounds. However, the computational burden to develop and deploy state-of-the-art models continuously increases, limiting their scalability. Most large-scale models are unimodal in nature and overlook the potential to leverage complementary molecular data modalities. To address these shortcomings, this paper introduces the Graph-Language Alignment for Chemical Inference and Exploration using Representations (GLACIER) model, a student-teacher framework that integrates molecular graphs, SMILES strings, and physicochemical descriptors to learn rich molecular embeddings. Our framework consists of three stages: (1) we pretrain three student encoders on 100,000 drug-like molecules: a message-passing neural network for molecular graphs, a transformer-based encoder for SMILES strings, and a multilayer perceptron for physicochemical descriptors, (2) we fuse these student modalities using a novel Finsler geometry-aware module, and (3) distill complementary knowledge from large teacher models, including MiniMol and MolFormer, into a single lightweight model via contrastive learning. We demonstrate that GLACIER is a robust framework that delivers high predictive performance and computational efficiency in complex molecular property prediction tasks. Our code is publicly available at https://github.com/eemokey/glacier.

  • Open Access

    Trustworthy Protein-Ligand Binding Affinity Prediction via Reliability-Aware Multi-Engine Fusion

    by Yongchan Hong, Defu Cao, Wenjin Liu, Thomas Ku, Jordy Homing Lam, Emily Nguyen, Willie Neiswanger, Vsevolod Katritch, Yan Liu

  • Open Access

    Coarse-to-Fine Multi-Resolution Diffusion Models for Trajectory Generation in Urban Systems

    by Wen Ye, Muyan Weng, Chuizheng Meng, Hao Niu, Yizhou Zhang, Yan Liu

  • Open Access

    Beyond Prediction: Toward Verifiable Physiological Waveform Reasoning: Advances, Challenges, and Future Directions

    by Xiaoda Wang, Ching Chang, Defu Cao, Kaiqiao Han, Fang Sun, Yue Huang, Minxiao Wang, Chang Xu, Xiao Luo, Runze Yan, et al.

  • Open Access

    Benchmarking computational methods for multi-omics biomarker discovery in cancer

    by Athan Z Li, Yuxuan Du, Yan Liu, Liang Chen, Ruishan Liu

    Multi-omics profiling characterizes cancer biology and supports biomarker discovery for prognosis and therapy selection. Although numerous computational multi-omics biomarker identification methods have been proposed, their ability to identify clinically relevant biomarkers has not been systematically evaluated, leaving it unclear whether the resulting biomarker nominations are reliable for downstream validation. Here, we systematically benchmark 20 representative statistical, machine learning and deep learning methods using curated gold-standard prognostic and therapeutic biomarkers across five real-world datasets. We evaluate performance in terms of both biomarker identification accuracy and stability. Overall, DeePathNet and DeepKEGG achieve the best performance. Across methods, effective biomarker recovery is associated with the integration of biological knowledge, global feature interactions, multivariate feature attribution, and effective regularization. Analysis of omics type contributions reveals method- and modality-specific biases, highlighting the importance of broader omics integration. We further evaluate methods on simulated datasets to probe sensitivity with controlled signal and noise. By aggregating results from top-performing methods, we construct consensus biomarker panels that nominate candidates for potential investigations. Finally, we provide user-friendly interfaces to allow researchers to benchmark new methods against the 20 baselines or apply selected methods for biomarker identification on custom multi-omics datasets. Our benchmark is publicly available at https://github.com/athanzli/CancerMOBI-Bench.


  • Open Access

    Benchmarking computational methods for multi-omics biomarker discovery in cancer

    by Athan Z. Li, Yuxuan Du, Yan Liu, Liang Chen, Ruishan Liu

    Multi-omics profiling characterizes cancer biology and supports biomarker discovery for prognosis and therapy selection. Although numerous computational multi-omics biomarker identification methods have been proposed, their ability to identify clinically relevant biomarkers has not been systematically evaluated, leaving it unclear whether the resulting biomarker nominations are reliable for downstream validation. Here we systematically benchmark 20 representative statistical, machine learning and deep learning methods using curated gold-standard prognostic and therapeutic biomarkers across five real-world datasets. We evaluate performance in terms of both biomarker identification accuracy and stability. Overall, DeePathNet and Deep-KEGG achieve the best performance. Across methods, effective biomarker recovery is associated with the integration of biological knowledge, global feature interactions, multivariate feature attribution, and effective regularization. Analysis of omics type contributions reveals method- and modality-specific biases, highlighting the importance of broader omics integration. We further evaluate methods on simulated datasets to probe sensitivity with controlled signal and noise. By aggregating results from top-performing methods, we construct consensus biomarker panels that nominate candidates for potential investigations. Finally, we provide user-friendly interfaces to allow researchers to benchmark new methods against the 20 baselines or apply selected methods for biomarker identification on custom multi-omics datasets. Our benchmark is publicly available at https://github.com/athanzli/CancerMOBI-Bench .


  • Open Access

    CartoMapQA: A Fundamental Benchmark Dataset Evaluating Vision-Language Models on Cartographic Map Understanding

    by Huy Quang Ung, Guillaume Habault, Yasutaka Nishimura, Hao Niu, Roberto Legaspi, Tomoki Oya, Ryoichi Kojima, Masato Taya, Chihiro Ono, Atsunori Minamikawa, et al.

    The rise of Visual-Language Models (LVLMs) has unlocked new possibilities for seamlessly integrating visual and textual information. However, their ability to interpret cartographic maps remains largely unexplored. In this paper, we introduce CartoMapQA, a benchmark specifically designed to evaluate LVLMs' understanding of cartographic maps through question-answering tasks. The dataset includes over 2000 samples, each composed of a cartographic map, a question (with open-ended or multiple-choice answers), and a ground-truth answer. These tasks span key low-, mid- and high-level map interpretation skills, including symbol recognition, embedded information extraction, scale interpretation, and route-based reasoning. Our evaluation of both open-source and proprietary LVLMs reveals persistent challenges: models frequently struggle with map-specific semantics, exhibit limited geospatial reasoning, and are prone to Optical Character Recognition (OCR)-related errors. By isolating these weaknesses, CartoMapQA offers a valuable tool for guiding future improvements in LVLM architectures. Ultimately, it supports the development of models better equipped for real-world applications that depend on robust and reliable map understanding, such as navigation, geographic search, and urban planning. Our source code and data are openly available to the research community at: https://github.com/ungquanghuy-kddi/CartoMapQA.git