Author name cluster

Zhaoxin Fan

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.

9 papers

2 author rows

AAAI Conference 2026 Conference Paper

Mem4D: Decoupling Static and Dynamic Memory for Dynamic Scene Reconstruction

Xudong Cai
Shuo Wang
Peng Wang
Yongcai Wang
Zhaoxin Fan
Wanting Li
Tianbao Zhang
Jianrong Tao

Reconstructing dense geometry for dynamic scenes from a monocular video is a critical yet challenging task. Recent memory-based methods enable efficient online reconstruction, but they fundamentally suffer from a Memory Demand Dilemma: The memory representation faces an inherent conflict between the long-term stability required for static structures and the rapid, high-fidelity detail retention needed for dynamic motion. This conflict forces existing methods into a compromise, leading to either geometric drift in static structures or blurred, inaccurate reconstructions of dynamic objects. To address this dilemma, we propose Mem4D, a novel framework that decouples the modeling of static geometry and dynamic motion. Guided by this insight, we design a dual-memory architecture: 1) The Transient Dynamics Memory (TDM) focuses on capturing high-frequency motion details from recent frames, enabling accurate and fine-grained modeling of dynamic content; 2) The Persistent Structure Memory (PSM) compresses and preserves long-term spatial information, ensuring global consistency and drift-free reconstruction for static elements. By alternating queries to these specialized memories, Mem4D simultaneously maintains static geometry with global consistency and reconstructs dynamic elements with high fidelity. Experiments on challenging benchmarks demonstrate that our method achieves state-of-the-art or competitive performance while maintaining high efficiency.

PDF Details DOI

AAAI Conference 2026 Conference Paper

MonoDream: Monocular Vision-Language Navigation with Panoramic Dreaming

Shuo Wang
Yongcai Wang
Zhaoxin Fan
Yucheng Wang
Maiyue Chen
Kaihui Wang
Zhizhong Su
Wanting Li

Vision-Language Navigation (VLN) tasks often leverage panoramic RGB and depth inputs to provide rich spatial cues for action planning, but these sensors can be costly or less accessible in real-world deployments. Recent approaches based on Vision-Language Action (VLA) models achieve strong results with monocular input, yet they still lag behind methods using panoramic RGB-D information. We present MonoDream, a lightweight VLA framework that enables monocular agents to learn a Unified Navigation Representation (UNR). This shared feature representation jointly aligns navigation-relevant visual semantics (e.g., global layout, depth, and future cues) and language-grounded action intent, enabling more reliable action prediction. MonoDream further introduces Latent Panoramic Dreaming (LPD) tasks to supervise the UNR, which train the model to predict latent features of panoramic RGB and depth observations at both current and future steps based on only monocular input. Experiments on multiple VLN benchmarks show that MonoDream consistently improves monocular navigation performance and significantly narrows the gap with panoramic-based agents.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Aux-Think: Exploring Reasoning Strategies for Data-Efficient Vision-Language Navigation

Shuo Wang
Yongcai Wang
Wanting Li
Xudong Cai
Yucheng Wang
Maiyue Chen
Zhizhong Su
Deying Li

Vision-Language Navigation is a critical task for developing embodied agents that can follow natural language instructions to navigate in complex real-world environments. Recent advances by finetuning large pretrained models have significantly improved generalization and instruction grounding compared to traditional approaches. However, the role of reasoning strategies in navigation—an action-centric, long-horizon task—remains underexplored, despite Chain-of-Thought reasoning's demonstrated success in static tasks like question answering and visual reasoning. To address this gap, we conduct the first systematic evaluation of reasoning strategies for VLN, including No-Think (direct action prediction), Pre-Think (reason before action), and Post-Think (reason after action). Surprisingly, our findings reveal the Inference-time Reasoning Collaps issue, where inference-time reasoning degrades navigation accuracy, highlighting the challenges of integrating reasoning into VLN. Based on this insight, we propose Aux-Think, a framework that trains models to internalize structured reasoning patterns through CoT supervision during training, while preserving No-Think inference for efficient action prediction. To support this framework, we release R2R-CoT-320k, a large-scale Chain-of-Thought annotated dataset. Empirically, Aux-Think significantly reduces training effort without compromising performance.

PDF Details

ICML Conference 2025 Conference Paper

EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers

Daiheng Gao
Shilin Lu
Wenbo Zhou 0004
Jiaming Chu
Jie Zhang 0073
Mengxi Jia
Bang Zhang
Zhaoxin Fan

Removing unwanted concepts from large-scale text-to-image (T2I) diffusion models while maintaining their overall generative quality remains an open challenge. This difficulty is especially pronounced in emerging paradigms, such as Stable Diffusion (SD) v3 and Flux, which incorporate flow matching and transformer-based architectures. These advancements limit the transferability of existing concept-erasure techniques that were originally designed for the previous T2I paradigm (e. g. , SD v1. 4). In this work, we introduce EraseAnything, the first method specifically developed to address concept erasure within the latest flow-based T2I framework. We formulate concept erasure as a bi-level optimization problem, employing LoRA-based parameter tuning and an attention map regularizer to selectively suppress undesirable activations. Furthermore, we propose a self-contrastive learning strategy to ensure that removing unwanted concepts does not inadvertently harm performance on unrelated ones. Experimental results demonstrate that EraseAnything successfully fills the research gap left by earlier methods in this new T2I paradigm, achieving state-of-the-art performance across a wide range of concept erasure tasks.

Details

IJCAI Conference 2025 Conference Paper

GLDiTalker: Speech-Driven 3D Facial Animation with Graph Latent Diffusion Transformer

Yihong Lin
Zhaoxin Fan
Xianjia Wu
Lingyu Xiong
Xiandong Li
Wenxiong Kang
Liang Peng
Songju Lei

Speech-driven talking head generation is a critical yet challenging task with applications in augmented reality and virtual human modeling. While recent approaches using autoregressive and diffusion-based models have achieved notable progress, they often suffer from modality inconsistencies, particularly misalignment between audio and mesh, leading to reduced motion diversity and lip-sync accuracy. To address this, we propose GLDiTalker, a novel speech-driven 3D facial animation model based on a Graph Latent Diffusion Transformer. GLDiTalker resolves modality misalignment by diffusing signals within a quantized spatiotemporal latent space. It employs a two-stage training pipeline: the Graph-Enhanced Quantized Space Learning Stage ensures lip-sync accuracy, while the Space-Time Powered Latent Diffusion Stage enhances motion diversity. Together, these stages enable GLDiTalker to generate realistic, temporally stable 3D facial animations. Extensive evaluations on standard benchmarks demonstrate that GLDiTalker outperforms existing methods, achieving superior results in both lip-sync accuracy and motion diversity.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Everything2Motion: Synchronizing Diverse Inputs via a Unified Framework for Human Motion Synthesis

Zhaoxin Fan
Longbin Ji
Pengxin Xu
Fan Shen
Kai Chen

In the dynamic field of film and game development, the emergence of human motion synthesis methods has revolutionized avatar animation. Traditional methodologies, typically reliant on single modality inputs like text or audio, employ modality-specific model frameworks, posing challenges for unified model deployment and application. To address this, we propose Everything2Motion, a unified model framework. Everything2Motion consists of three key modules. The Input-Output Modality Modulation module tailors structures for specific multimodal inputs, eliminating the need for modality-specific frameworks. The Query-aware Autoencoder, based on the transformer encoder-decoder architecture, enables efficient latent motion generation. Lastly, the Prior Motion Distillation Decoder, a pretrained module, enhances the final skeleton sequence's naturalness and fluidity. Comprehensive experiments on several public datasets demonstrate the effectiveness of Everything2Motion, highlighting its potential for practical applications and setting a new benchmark in human motion synthesis.

PDF Details DOI

ICRA Conference 2023 Conference Paper

GIDP: Learning a Good Initialization and Inducing Descriptor Post-enhancing for Large-scale Place Recognition

Zhaoxin Fan
Zhenbo Song
Hongyan Liu 0002
Jun He 0008

Large-scale place recognition is a fundamental but challenging task, which plays an increasingly important role in autonomous driving and robotics. Existing methods have achieved acceptable good performance, however, most of them are concentrating on designing elaborate global descriptor learning network structures. The importance of feature generalization and descriptor post-enhancing has long been neglected. In this work, we propose a novel method named GIDP to learn a Good Initialization and Inducing Descriptor Pose-enhancing for Large-scale Place Recognition. In particular, an unsupervised momentum contrast point cloud pretraining module and a reranking-based descriptor post-enhancing module are proposed respectively in GIDP. The former aims at learning a good initialization for the point cloud encoding network before training the place recognition model, while the later aims at post-enhancing the predicted global descriptor through reranking at inference time. Ex-tensive experiments on both indoor and outdoor datasets demonstrate that our method can achieve state-of-the-art performance using simple and general point cloud encoding backbones.

Details

IJCAI Conference 2023 Conference Paper

Reconstruction-Aware Prior Distillation for Semi-supervised Point Cloud Completion

Zhaoxin Fan
Yulin He
Zhicheng Wang
Kejian Wu
Hongyan Liu
Jun He

Real-world sensors often produce incomplete, irregular, and noisy point clouds, making point cloud completion increasingly important. However, most existing completion methods rely on large paired datasets for training, which is labor-intensive. This paper proposes RaPD, a novel semi-supervised point cloud completion method that reduces the need for paired datasets. RaPD utilizes a two-stage training scheme, where a deep semantic prior is learned in stage 1 from unpaired complete and incomplete point clouds, and a semi-supervised prior distillation process is introduced in stage 2 to train a completion network using only a small number of paired samples. Additionally, a self-supervised completion module is introduced to improve performance using unpaired incomplete point clouds. Experiments on multiple datasets show that RaPD outperforms previous methods in both homologous and heterologous scenarios.

PDF Details DOI

AAAI Conference 2022 Conference Paper

SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition

Zhaoxin Fan
Zhenbo Song
Hongyan Liu
Zhiwu Lu
Jun He
Xiaoyong Du

Simultaneous Localization and Mapping (SLAM) and Autonomous Driving are becoming increasingly more important in recent years. Point cloud-based large scale place recognition is the spine of them. While many models have been proposed and have achieved acceptable performance by learning short-range local features, they always skip long-range contextual properties. Moreover, the model size also becomes a serious shackle for their wide applications. To overcome these challenges, we propose a super light-weight network model termed SVT-Net. On top of the highly efficient 3D Sparse Convolution (SP-Conv), an Atom-based Sparse Voxel Transformer (ASVT) and a Cluster-based Sparse Voxel Transformer (CSVT) are proposed respectively to learn both shortrange local features and long-range contextual features. Consisting of ASVT and CSVT, SVT-Net can achieve state-ofthe-art performance in terms of both recognition accuracy and running speed with a super-light model size (0. 9M parameters). Meanwhile, for the purpose of further boosting efficiency, we introduce two simplified versions, which also achieve state-of-the-art performance and further reduce the model size to 0. 8M and 0. 4M respectively.

PDF Details