Author name cluster

Zichen Wen

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.

8 papers

2 author rows

AAAI Conference 2026 Conference Paper

D²Pruner: Debiased Importance and Structural Diversity for MLLM Token Pruning

Evelyn Zhang
Fufu Yu
Aoqi Wu
Zichen Wen
Ke Yan
Shouhong Ding
Biqing Qi
Linfeng Zhang

Processing long visual token sequences poses a significant computational burden on Multimodal Large Language Models (MLLMs). While token pruning offers a path to acceleration, we find that current methods, while adequate for general understanding, catastrophically fail on fine-grained localization tasks. We attribute this failure to the inherent flaws of the two prevailing strategies: importance-based methods suffer from a strong positional bias, an inherent model artifact that distracts from semantic content, while diversity-based methods exhibit structural blindness, disregarding the user's prompt and spatial redundancy. To address this, we introduce D²Pruner, a framework that rectifies these issues by uniquely combining debiased importance with a structural pruning mechanism. Our method first secures a core set of the most critical tokens as pivots based on a debiased attention score. It then performs a Maximal Independent Set (MIS) selection on the remaining tokens, which are modeled on a hybrid graph where edges signify spatial proximity and semantic similarity. This process iteratively preserves the most important and available token while removing its neighbors, ensuring that the supplementary tokens are chosen to maximize importance and diversity. Extensive experiments demonstrate that D²Pruner achieves exceptional efficiency and fidelity.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Efficient Multi-modal Large Language Models via Progressive Consistency Distillation

Zichen Wen
Shaobo Wang
Yufa Zhou
Junyuan Zhang
Qintong Zhang
Yifeng Gao
Zhaorun Chen
Bin Wang

Visual tokens consume substantial computational resources in multi-modal large models (MLLMs), significantly compromising their efficiency. Recent works have attempted to improve efficiency by compressing visual tokens during training, either through modifications to model components or by introducing additional parameters. However, they often overlook the increased learning difficulty caused by such compression, as the model’s parameter space struggles to quickly adapt to the substantial perturbations in the feature space induced by token compression. In this work, we propose to develop Efficient MLLMs via Progressive Consistency Distillation (EPIC), a progressive learning framework. Specifically, by decomposing the feature space perturbations introduced by token compression along the token-wise and layer-wise dimensions, we introduce token consistency distillation and layer consistency distillation, respectively, aiming to reduce the training difficulty by leveraging guidance from a teacher model and following a progressive learning trajectory. Extensive experiments demonstrate the superior effectiveness, robustness, and generalization capabilities of our proposed framework.

PDF Details

NeurIPS Conference 2025 Conference Paper

EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models

Yantai Yang
Yuhao Wang
Zichen Wen
Luo Zhongwei
Chang Zou
Zhipeng Zhang
Chuan Wen
Linfeng Zhang

Vision-Language-Action (VLA) models, particularly diffusion-based architectures, demonstrate transformative potential for embodied intelligence but are severely hampered by high computational and memory demands stemming from extensive inherent and inference-time redundancies. While existing acceleration efforts often target isolated inefficiencies, such piecemeal solutions typically fail to holistically address the varied computational and memory bottlenecks across the entire VLA pipeline, thereby limiting practical deployability. We introduce EfficientVLA, a structured and training-free inference acceleration framework that systematically eliminates these barriers by cohesively exploiting multifaceted redundancies. EfficientVLA synergistically integrates three targeted strategies: (1) pruning of functionally inconsequential layers from the language module, guided by an analysis of inter-layer redundancies; (2) optimizing the visual processing pathway through a task-aware strategy that selects a compact, diverse set of visual tokens, balancing task-criticality with informational coverage; and (3) alleviating temporal computational redundancy within the iterative diffusion-based action head by strategically caching and reusing key intermediate features. We apply our method to a standard VLA model CogACT, yielding a $1. 93\times$ inference speedup and reduces FLOPs to 28. 9%, with only a 0. 6% success rate drop in the SIMPLER benchmark.

PDF Details

NeurIPS Conference 2025 Conference Paper

MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?

Zhaorun Chen
Zichen Wen
Yichao Du
Yiyang Zhou
Chenhang Cui
Siwei Han
Jen Weng
Chaoqi Wang

While text-to-image models like GPT-4o-Image and FLUX are rapidly proliferating, they often encounter challenges such as hallucination, bias, and the production of unsafe, low-quality output. To effectively address these issues, it is crucial to align these models with desired behaviors based on feedback from a multimodal judge. Despite their significance, current multimodal judges frequently undergo inadequate evaluation of their capabilities and limitations, potentially leading to misalignment and unsafe fine-tuning outcomes. To address this issue, we introduce MJ-Bench, a novel benchmark which incorporates a comprehensive preference dataset to evaluate multimodal judges in providing feedback for image generation models across six key perspectives: alignment, safety, image quality, bias, composition, and visualization. Specifically, we evaluate a large variety of multimodal judges including smaller-sized CLIP-based scoring models, open-source VLMs, and close-source VLMs on each decomposed subcategory of our preference dataset. Experiments reveal that close-source VLMs generally provide better feedback, with GPT-4o outperforming other judges in average. Compared with open-source VLMs, smaller-sized scoring models can provide better feedback regarding text-image alignment and image quality, while VLMs provide more accurate feedback regarding safety and generation bias due to their stronger reasoning capabilities. Further studies in feedback scale reveal that VLM judges can generally provide more accurate and stable feedback in natural language than numerical scales. Notably, human evaluations on end-to-end and fine-tuned models using separate feedback from these multimodal judges provide similar conclusions, further confirming the effectiveness of MJ-Bench.

PDF Details

ICML Conference 2025 Conference Paper

Multi-View Graph Clustering via Node-Guided Contrastive Encoding

Yazhou Ren 0001
Junlong Ke
Zichen Wen
Tianyi Wu
Yang Yang 0002
Xiaorong Pu
Lifang He 0001

Multi-view clustering has gained significant attention for integrating multi-view information in multimedia applications. With the growing complexity of graph data, multi-view graph clustering (MVGC) has become increasingly important. Existing methods primarily use Graph Neural Networks (GNNs) to encode structural and feature information, but applying GNNs within contrastive learning poses specific challenges, such as integrating graph data with node features and handling both homophilic and heterophilic graphs. To address these challenges, this paper introduces Node-Guided Contrastive Encoding (NGCE), a novel MVGC approach that leverages node features to guide embedding generation. NGCE enhances compatibility with GNN filtering, effectively integrates homophilic and heterophilic information, and strengthens contrastive learning across views. Extensive experiments demonstrate its robust performance on six homophilic and heterophilic multi-view benchmark datasets.

Details

NeurIPS Conference 2025 Conference Paper

Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation

Siwei Wen
Junyan Ye
Peilin Feng
Hengrui Kang
Zichen Wen
Yize Chen
Jiang Wu
Wenjun Wu

With the rapid advancement of Artificial Intelligence Generated Content (AIGC) technologies, synthetic images have become increasingly prevalent in everyday life, posing new challenges for authenticity assessment and detection. Despite the effectiveness of existing methods in evaluating image authenticity and locating forgeries, these approaches often lack human interpretability and do not fully address the growing complexity of synthetic data. To tackle these challenges, we introduce FakeVLM, a specialized large multimodal model designed for both general synthetic image and DeepFake detection tasks. FakeVLM not only excels in distinguishing real from fake images but also provides clear, natural language explanations for image artifacts, enhancing interpretability. Additionally, we present FakeClue, a comprehensive dataset containing over 100, 000 images across seven categories, annotated with fine-grained artifact clues in natural language. FakeVLM demonstrates performance comparable to expert models while eliminating the need for additional classifiers, making it a robust solution for synthetic data detection. Extensive evaluations across multiple datasets confirm the superiority of FakeVLM in both authenticity classification and artifact explanation tasks, setting a new benchmark for synthetic image detection. The code, model weights, and dataset can be found here: https: //github. com/opendatalab/FakeVLM.

PDF Details

AAAI Conference 2024 Conference Paper

Homophily-Related: Adaptive Hybrid Graph Filter for Multi-View Graph Clustering

Zichen Wen
Yawen Ling
Yazhou Ren
Tianyi Wu
Jianpeng Chen
Xiaorong Pu
Zhifeng Hao
Lifang He

Recently there is a growing focus on graph data, and multi-view graph clustering has become a popular area of research interest. Most of the existing methods are only applicable to homophilous graphs, yet the extensive real-world graph data can hardly fulfill the homophily assumption, where the connected nodes tend to belong to the same class. Several studies have pointed out that the poor performance on heterophilous graphs is actually due to the fact that conventional graph neural networks (GNNs), which are essentially low-pass filters, discard information other than the low-frequency information on the graph. Nevertheless, on certain graphs, particularly heterophilous ones, neglecting high-frequency information and focusing solely on low-frequency information impedes the learning of node representations. To break this limitation, our motivation is to perform graph filtering that is closely related to the homophily degree of the given graph, with the aim of fully leveraging both low-frequency and high-frequency signals to learn distinguishable node embedding. In this work, we propose Adaptive Hybrid Graph Filter for Multi-View Graph Clustering (AHGFC). Specifically, a graph joint process and graph joint aggregation matrix are first designed by using the intrinsic node features and adjacency relationship, which makes the low and high-frequency signals on the graph more distinguishable. Then we design an adaptive hybrid graph filter that is related to the homophily degree, which learns the node embedding based on the graph joint aggregation matrix. After that, the node embedding of each view is weighted and fused into a consensus embedding for the downstream task. Experimental results show that our proposed model performs well on six datasets containing homophilous and heterophilous graphs.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Integrating Vision-Language Semantic Graphs in Multi-View Clustering

JunLong Ke
Zichen Wen
Yechenhao Yang
Chenhang Cui
Yazhou Ren
Xiaorong Pu
Lifang He

In recent years, a variety of graph learning-based multi-view clustering (MVC) methods have emerged. However, these methods continue to face challenges in extracting latent features from real-world data, particularly in scenarios involving high-resolution color images and high-dimensional features. This task is notably difficult in cases where images are visually similar yet semantically diverse. To address this issue, we present a novel large-scale pre-trained model for multi-view clustering, named Integrate Vision-Language Semantic Graphs in Multi-View Clustering (IVSGMV), which harnesses the capabilities of visual-language pre-training models to enhance clustering performance and confronts issues in the unsupervised tuning of pre-trained models for multi-view data. We introduce an effective unsupervised approach for creating semantic graphs from image multi-view datasets using pre-trained encoders. Our method addresses the inherent spatial noise and imbalance in these encoders by employing graph filters and a joint process that integrates both image node and edge features. Additionally, we demonstrate the application of our approach to multi-view image clustering on extensive datasets, notably the high-resolution MVImgNet, achieving an impressive 82% accuracy. Furthermore, our method extends the zero-shot capabilities of large-scale pre-trained models, resulting in good performance in clustering tasks on untrained multi-view datasets.

PDF Details DOI