Author name cluster

Xin Zou

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.

10 papers

1 author row

AAAI Conference 2026 Conference Paper

PLA-MGRA: Multi-Granularity and Relation-Aware Learning for Efficient and Generalizable Protein-Ligand Binding Affinity Prediction

Shunfan Li
Jiangkai Long
Xin Zou
Chang Tang
Yuanyuan Liu
Xiao He
Xuesong Yan

Protein-Ligand Affinity (PLA) prediction quantifies the interaction strength to guide rational drug design. Existing approaches typically analyze interaction at a single granularity and overlook tightly coupled relationships between protein and ligand in both structure and functionality, consequently yielding suboptimal representations, leading to significant performance drops in real-world scenarios. To address this problem, we propose PLA-MGRA, a minimalist and effective PLA prediction framework. Specifically, PLA-MGRA captures both fine-grained atomic details and coarse grained functional semantics within the 3D structure of protein–ligand complexes, through multi-granularity learning. To further parse the coupled protein–ligand relationships, we design relation-aware learning to enhance the binding nature of representations. Extensive experiments demonstrate that our method achieves state-of-the-art performance on multiple protein–ligand affinity prediction benchmarks, while also offering generalizability and interpretability.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Sharp Eyes and Memory for VideoLLMs: Information-Aware Visual Token Pruning for Efficient and Reliable VideoLLM Reasoning

Jialong Qin
Xin Zou
Di Lu
Yibo Yan
Xuming Hu

Current Video Large Language Models (VideoLLMs) suffer from quadratic computational complexity and key-value cache scaling, due to their reliance on processing excessive redundant visual tokens. To address this problem, we propose SharpV, a minimalist and efficient method for adaptive pruning of visual tokens and KV cache. Different from most uniform compression approaches, SharpV dynamically adjusts pruning ratios based on spatial-temporal information. Remarkably, this adaptive mechanism occasionally achieves performance gains over dense models, offering a novel paradigm for adaptive pruning. During the KV cache pruning stage, based on observations of visual information degradation, SharpV prunes degraded visual features via a self-calibration manner, guided by similarity to original visual features. In this way, SharpV achieves hierarchical cache pruning from the perspective of information bottleneck, offering a new insight into VideoLLMs' information flow. Experiments on multiple public benchmarks demonstrate the superiority of SharpV. Moreover, to the best of our knowledge, SharpV is notably the first two-stage pruning framework that operates without requiring access to exposed attention scores, ensuring full compatibility with hardware acceleration techniques like Flash Attention.

PDF Details DOI

EAAI Journal 2025 Journal Article

Cancer–drug response prediction via feature aggregation and association graph learning

Kaiyi Xu
Minhui Wang
Xin Zou
Chengfu Ji
Hua Zhou
Chang Tang

Predicting cancer–drug response (CDR) not only guides the development of anticancer drugs but also provides personalized treatment plans for cancer patients, driving the advancement of precision medicine. Currently, numerous computational methods are utilized for CDR prediction and achieve great achievements. However, there are still some issues need to be addressed. From the aspect of data using, many studies primarily use single nucleotide variations (SNV) as features of cell lines, yet their acquisition from clinical data is often incomplete and inefficient, making it challenging to extend SNV-based CDR models from in vitro cell lines to clinical data. From the aspect of modeling, most works focus excessively on learning the intrinsic characteristics of drugs and cell lines, while neglecting to fully capture their interaction information and network-level knowledge. In this paper, we introduce a feature aggregation and association graph learning network (F A 2 GL) for CDR, which aggregates intrinsic and interaction feature representations of drugs and cell lines, and obtains their network-level knowledge from the association graph. In this network, F A 2 GL initially employs the self-attention block (SAB) to capture drug intrinsic features, with a focus on the relationships between substructures within the same drug, and utilizes the multilayer perceptron (MLP) to obtain cell line intrinsic features. Subsequently, it constructs the cross-attention block (CAB) to extract interaction information between drugs and cell lines, followed by the utilization of a fusion coefficient for aggregating these features. Additionally, F A 2 GL also constructs an association graph by introducing pipe nodes and similarity networks, bridging the feature gap between drugs and cell lines and enhancing predictions of similar substances, respectively. Then, a graph neural network (GNN) is applied to this graph to capture their network-level information. By integrating fine-grained and network-level features, F A 2 GL demonstrates competitiveness compared to state-of-the-art methods on Genomics of Drug Sensitivity in Cancer (GDSC) dataset which contains various cancers such as acute lymphoblastic leukemia, diffuse large B-Cell lymphoma, and multiple myeloma, while avoiding the use of large-scale SNV data. The codes and data for F A 2 GL are available at https: //github. com/Dtdtxuky/FA-2GL/tree/main.

Details DOI

NeurIPS Conference 2025 Conference Paper

Don't Just Chase “Highlighted Tokens” in MLLMs: Revisiting Visual Holistic Context Retention

Xin Zou
Di Lu
Yizhou Wang
Yibo Yan
Yuanhuiyi Lyu
Xu Zheng
Linfeng Zhang
Xuming Hu

Despite their powerful capabilities, multimodal large language models (MLLMs) suffer from considerable computational overhead due to their reliance on massive visual tokens. Recent studies have explored token pruning to alleviate this problem, which typically uses text-vision cross-attention or [CLS] attention to assess and discard redundant visual tokens. In this work, we identify a critical limitation of such attention-first pruning approaches, i. e. , they tend to preserve semantically similar tokens, resulting in pronounced performance drops under high pruning rates. To this end, we propose HoloV, a simple yet effective, plug-and-play visual token pruning framework for efficient inference. Distinct from previous attention-first schemes, HoloV rethinks token retention from a holistic perspective. By adaptively distributing the pruning budget across different spatial crops, HoloV ensures that the retained tokens capture the global visual context rather than isolated salient features. This strategy minimizes representational collapse and maintains task-relevant information even under aggressive pruning. Experimental results demonstrate that our HoloV achieves superior performance across various tasks, MLLM architectures, and pruning ratios compared to SOTA methods. For instance, LLaVA1. 5 equipped with HoloV preserves 95. 8% of the original performance after pruning 88. 9% of visual tokens, achieving superior efficiency-accuracy trade-offs.

PDF Details

NeurIPS Conference 2025 Conference Paper

SparseMVC: Probing Cross-view Sparsity Variations for Multi-view Clustering

Ruimeng Liu
Xin Zou
Chang Tang
Xiao Zheng
Xingchen Hu
Kun Sun
Xinwang Liu

Existing multi-view clustering methods employ various strategies to address data-level sparsity and view-level dynamic fusion. However, we identify a critical yet overlooked issue: varying sparsity across views. Cross-view sparsity variations lead to encoding discrepancies, heightening sample-level semantic heterogeneity and making view-level dynamic weighting inappropriate. To tackle these challenges, we propose Adaptive Sparse Autoencoders for Multi-View Clustering (SparseMVC), a framework with three key modules. Initially, the sparse autoencoder probes the sparsity of each view and adaptively adjusts encoding formats via an entropy-matching loss term, mitigating cross-view inconsistencies. Subsequently, the correlation-informed sample reweighting module employs attention mechanisms to assign weights by capturing correlations between early-fused global and view-specific features, reducing encoding discrepancies and balancing contributions. Furthermore, the cross-view distribution alignment module aligns feature distributions during the late fusion stage, accommodating datasets with an arbitrary number of views. Extensive experiments demonstrate that SparseMVC achieves state-of-the-art clustering performance. Our framework advances the field by extending sparsity handling from the data-level to view-level and mitigating the adverse effects of encoding discrepancies through sample-level dynamic weighting. The source code is publicly available at https: //github. com/cleste-pome/SparseMVC.

PDF Details

NeurIPS Conference 2024 Conference Paper

A Boosting-Type Convergence Result for AdaBoost.MH with Factorized Multi-Class Classifiers

Xin Zou
Zhengyu Zhou
Jingyuan Xu
Weiwei Liu

AdaBoost is a well-known algorithm in boosting. Schapire and Singer propose, an extension of AdaBoost, named AdaBoost. MH, for multi-class classification problems. Kégl shows empirically that AdaBoost. MH works better when the classical one-against-all base classifiers are replaced by factorized base classifiers containing a binary classifier and a vote (or code) vector. However, the factorization makes it much more difficult to provide a convergence result for the factorized version of AdaBoost. MH. Then, Kégl raises an open problem in COLT 2014 to look for a convergence result for the factorized AdaBoost. MH. In this work, we resolve this open problem by presenting a convergence result for AdaBoost. MH with factorized multi-class classifiers.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Coverage-Guaranteed Prediction Sets for Out-of-Distribution Data

Xin Zou
Weiwei Liu

Out-of-distribution (OOD) generalization has attracted increasing research attention in recent years, due to its promising experimental results in real-world applications. In this paper, we study the confidence set prediction problem in the OOD generalization setting. Split conformal prediction (SCP) is an efficient framework for handling the confidence set prediction problem. However, the validity of SCP requires the examples to be exchangeable, which is violated in the OOD setting. Empirically, we show that trivially applying SCP results in a failure to maintain the marginal coverage when the unseen target domain is different from the source domain. To address this issue, we develop a method for forming confident prediction sets in the OOD setting and theoretically prove the validity of our method. Finally, we conduct experiments on simulated data to empirically verify the correctness of our theory and the validity of our proposed method.

PDF Details DOI

JBHI Journal 2024 Journal Article

DAI-Net: Dual Adaptive Interaction Network for Coordinated Medication Recommendation

Xin Zou
Xiao He
Xiao Zheng
Wei Zhang
Jiajia Chen
Chang Tang

Medication recommendation is a productive task for AI-driven healthcare systems, which can assist clinicians in prescribing judicious and effective treatments. However, existing medication recommendation methods omit two key pieces of information: Coarse-grained interaction information between distinct types of symptoms in a patient's medical history and corresponding medication representations can serve as attention for predicting the current medication combinations of the patient. Fine-grained interaction information between medication substructure representations and different types of symptoms can facilitate the construction of molecular-level disentangled medication representations. To address this dilemma, we propose a novel D ual A daptive I nteraction Net work (DAI-Net), which encodes comprehensive interaction knowledge between patients' multifaceted health records and medication molecules to improve the performance of medication recommendation and heighten interpretability of the model. Specifically, we design a symptom-aware medication matching module to extract coordinated associations between patient symptoms and medication molecules, coarse-grained interaction learning. The medication embeddings are utilized to transform patient-medication matching properties into a symptom-substructure matching matrix for fine-grained interaction. The patient's Longitudinal representation is employed as a query to decode both symptom-medication and symptom-substructure matching information for coordinated medication representation. DAI-Net is an end-to-end recommendation model. Extensive experiments on the real-world EHR datasets, i. e. , the public benchmark MIMIC-III, MIMIC-IV, and eICU, demonstrate that the proposed DAI-Net achieves competitive performance compared to other state-of-the-art ones, with an average improvement of 1. 8%, 2. 1% in Jaccard on MIMIC-III and -IV dataset.

Details DOI

JMLR Journal 2023 Journal Article

Generalization Bounds for Adversarial Contrastive Learning

Xin Zou
Weiwei Liu

Deep networks are well-known to be fragile to adversarial attacks, and adversarial training is one of the most popular methods used to train a robust model. To take advantage of unlabeled data, recent works have applied adversarial training to contrastive learning (Adversarial Contrastive Learning; ACL for short) and obtain promising robust performance. However, the theory of ACL is not well understood. To fill this gap, we leverage the Rademacher omplexity to analyze the generalization performance of ACL, with a particular focus on linear models and multi-layer neural networks under $\ell_p$ attack ($p \ge 1$). Our theory shows that the average adversarial risk of the downstream tasks can be upper bounded by the adversarial unsupervised risk of the upstream task. The experimental results validate our theory. [abs] [ pdf ][ bib ] &copy JMLR 2023. ( edit, beta )

PDF Details

NeurIPS Conference 2023 Conference Paper

On the Adversarial Robustness of Out-of-distribution Generalization Models

Xin Zou
Weiwei Liu

Out-of-distribution (OOD) generalization has attracted increasing research attention in recent years, due to its promising experimental results in real-world applications. Interestingly, we find that existing OOD generalization methods are vulnerable to adversarial attacks. This motivates us to study OOD adversarial robustness. We first present theoretical analyses of OOD adversarial robustness in two different complementary settings. Motivated by the theoretical results, we design two algorithms to improve the OOD adversarial robustness. Finally, we conduct experiments to validate the effectiveness of our proposed algorithms.

PDF Details