Author name cluster

Xu Zhao

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.

7 papers

1 author row

EAAI Journal 2026 Journal Article

A risk-aware driving agent with Long Short-Term Memory and Time-to-Collision co-decision and multi-modal fusion in urban simulation

Xu Zhao
Yu Gao
Wen Liu
Lianpeng Li
Suxian Zhang
Zijun Wang

We present a risk-aware driving agent for urban freeway settings that combines Long Short-Term Memory (LSTM) motion prediction with a dynamic Time-to-Collision (TTC) safety gate. Light Detection and Ranging (LiDAR), point-cloud radar, and camera inputs are fused in a unified interface; the decision layer predicts lead-vehicle acceleration and combines it with TTC that reflects road adhesion, braking capability, and obstacle confidence. A finite-state machine with hysteresis maps TTC to four discrete risk actions: safe, warning, prepare, and automatic emergency braking (AEB). The enhanced version adds multi-target Kalman tracking, adaptive TTC parameters, and physics-aware acceleration limits. The TTC gate remains explicit. A Transformer-based fusion backbone and a deep Q-network (DQN) planner process heterogeneous sensor features. In this engineering artificial intelligence application for autonomous driving and intelligent transportation systems, the implemented artificial intelligence modules (including LSTM prediction, attention-based multi-modal fusion, and DQN planning) operate under the same TTC-based safety logic so that risk metrics and braking bounds remain explicit. Experiments cover a 60-second, 1. 9-kilometer free-flow run and two scripted hazards: an aggressive cut-in (minimum headway 0. 64 meters, minimum TTC 0. 07 s, warning/prepare/automatic emergency braking occupancy 48. 8%, with 10. 8% automatic emergency braking) and a pedestrian crossing (minimum pedestrian gap 3. 1 meters, warning/prepare/automatic emergency braking occupancy 48. 0%). A TTC-parameter sweep and a TTC-only ablation show that the current thresholds are conservative in benign cases and that calibration should focus on sharper hazards. The agent design and logs provide a transparent baseline for longitudinal risk-aware control.

Details DOI

AAAI Conference 2026 Conference Paper

Diffusion-based Personalized Pathology Disentanglement for Impaired Gait Analysis

Xiaoyue Wan
Xu Zhao

In the context of global population aging, the prevalence of neurodegenerative diseases is rapidly increasing. Vision-based impaired gait analysis emerges as a promising alternative for automatic and non-invasive diagnosis. While prior efforts have advanced either accuracy or interpretability of gait analysis, few have effectively addressed both aspects in a unified framework. To bridge this gap, we propose DPPD, a Diffusion-based Personalized Pathology Disentanglement model that jointly performs quantitative gait scoring, dementia subtyping, and qualitative anomaly highlighting. Motivated by the observation that pathological gait features exhibit stronger inter-class separability across different gait severity than raw features, DPPD is proposed based on the subject-specific pathology disentanglement perspective. Specifically, it comprises three key components: (1) a 3DmotionBERT for encoding gait representation from 3D human pose sequences estimated, (2) a latent diffusion-based Gait Denoiser for generating personalized normal gait features, and (3) a Dual Pathology Disentanglement mechanism that captures both static pose and dynamic motion pathological representation from the residual between raw and normal gait features. These disentangled pathologies further enable quantitative classification and qualitative anomaly highlighting. Experiments on the PDGait and 3DGait datasets demonstrate that DPPD outperforms state-of-the-art methods in classification accuracy while providing reliable and interpretable visualizations of gait anomalies.

PDF Details DOI

AAAI Conference 2026 Conference Paper

LiViBench: An Omnimodal Benchmark for Interactive Livestream Video Understanding

Xiaodong Wang
Langling Huang
Zhirong Wu
Xu Zhao
Teng Xu
Xuhong Xia
Peixi Peng

The development of multimodal large language models (MLLMs) has advanced general video understanding. However, existing video evaluation benchmarks primarily focus on non-interactive videos, such as movies and recordings. To fill this gap, this paper proposes the first omnimodal benchmark for interactive livestream videos, LiViBench. It features a diverse set of 24 tasks, highlighting the perceptual, reasoning, and livestream-specific challenges. To efficiently construct the dataset, we design a standardized semi-automatic annotation workflow that incorporates the human-in-the-loop at multiple stages. The workflow leverages multiple MLLMs to form a multi-agent system for comprehensive video description and uses a seed-question-driven method to construct high-quality annotations. All interactive videos in the benchmark include audio, speech, and real-time comments modalities. To enhance models' understanding of interactive videos, we design tailored two-stage instruction-tuning and propose a Video-to-Comment Retrieval (VCR) module to improve the model's ability to utilize real-time comments. Based on these advancements, we develop LiVi-LLM-7B, an MLLM with enhanced knowledge of interactive livestreams. Experiments show that our model outperforms larger open-source models with up to 72B parameters, narrows the gap with leading proprietary models on LiViBench, and achieves enhanced performance on general video benchmarks, including VideoMME, LongVideoBench, MLVU, and VideoEval-Pro.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Exploiting Multimodal Spatial-temporal Patterns for Video Object Tracking

Xiantao Hu
Ying Tai
Xu Zhao
Chen Zhao
Zhenyu Zhang
Jun Li
Bineng Zhong
Jian Yang

Multimodal tracking has garnered widespread attention as a result of its ability to effectively address the inherent limitations of traditional RGB tracking. However, existing multimodal trackers mainly focus on the fusion and enhancement of spatial features or merely leverage the sparse temporal relationships between video frames. These approaches do not fully exploit the temporal correlations in multimodal videos, making it difficult to capture the dynamic changes and motion information of targets in complex scenarios. To alleviate this problem, we propose a unified multimodal spatial-temporal tracking approach named STTrack. In contrast to previous paradigms that solely relied on updating reference information, we introduced a temporal state generator (TSG) that continuously generates a sequence of tokens containing multimodal temporal information. These temporal information tokens are used to guide the localization of the target in the next time state, establish long-range contextual relationships between video frames, and capture the temporal trajectory of the target. Furthermore, at the spatial level, we introduced the mamba fusion and background suppression interactive (BSI) modules. These modules establish a dual-stage mechanism for coordinating information interaction and fusion between modalities. Extensive comparisons on five benchmark datasets illustrate that STTrack achieves state-of-the-art performance across various multimodal tracking scenarios.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

Public Signaling in Markets with Information Asymmetry Using a Limited Number of Signals

Xu Zhao
Ren Liu
Weiran Shen

Consider a market with a seller and many buyers. The seller has a kind of item for sale to the buyers. The items have a quality and each buyer has a private type. The quality is only known to the seller, and the buyers only have a prior belief of the quality. A third party (e. g. , intermediaries or product reviewers) is able to reveal information about the actual quality by using a so-called signaling scheme. After receiving the information, buyers can update their beliefs accordingly and decide whether to buy the items. We consider the third party's problem of maximizing the purchasing probability by sending signals. However, the optimal signaling scheme has implementation issues, as the number of signals in the optimal scheme is the same as the number of buyer types, which can be exceedingly large or even infinite. We therefore investigate whether a finite and limited set of signals could still approximate the performance of the optimal signaling scheme. Unfortunately, our results show that with a finite number of signals, no signaling scheme can achieve a certain fraction of the performance of the optimal signaling scheme. This limitation persists even with the regularity or the monotone hazard rate assumption. Nevertheless, we identify a mild technical condition under which the third party can approximate the optimal performance within a constant factor by employing only two signals. We also conduct extensive experiments to substantiate our theoretic results. These experiments compare the performance of using a small signal set across different value distributions. Despite the negative results, our experiment results show that using only a small number of signals is able to achieve a fairly reasonable performance in average cases.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Dual-Diffusion for Binocular 3D Human Pose Estimation

Xiaoyue Wan
Zhuo Chen
Bingzhi Duan
Xu Zhao

Binocular 3D human pose estimation (HPE), reconstructing a 3D pose from 2D poses of two views, offers practical advantages by combining multiview geometry with the convenience of a monocular setup. However, compared to a multiview setup, the reduction in the number of cameras increases uncertainty in 3D reconstruction. To address this issue, we leverage the diffusion model, which has shown success in monocular 3D HPE by recovering 3D poses from noisy data with high uncertainty. Yet, the uncertainty distribution of initial 3D poses remains unknown. Considering that 3D errors stem from 2D errors within geometric constraints, we recognize that the uncertainties of 3D and 2D are integrated in a binocular configuration, with the initial 2D uncertainty being well-defined. Based on this insight, we propose Dual-Diffusion specifically for Binocular 3D HPE, simultaneously denoising the uncertainties in 2D and 3D, and recovering plausible and accurate results. Additionally, we introduce Z-embedding as an additional condition for denoising and implement baseline-width-related pose normalization to enhance the model flexibility for various baseline settings. This is crucial as 3D error influence factors encompass depth and baseline width. Extensive experiments validate the effectiveness of our Dual-Diffusion in 2D refinement and 3D estimation. The code and models are available at https: //github. com/sherrywan/Dual-Diffusion.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Fluctuation-Based Adaptive Structured Pruning for Large Language Models

Yongqi An
Xu Zhao
Tao Yu
Ming Tang
Jinqiao Wang

Network Pruning is a promising way to address the huge computing resource demands of the deployment and inference of Large Language Models (LLMs). Retraining-free is important for LLMs' pruning methods. However, almost all of the existing retraining-free pruning approaches for LLMs focus on unstructured pruning, which requires specific hardware support for acceleration. In this paper, we propose a novel retraining-free structured pruning framework for LLMs, named FLAP (FLuctuation-based Adaptive Structured Pruning). It is hardware-friendly by effectively reducing storage and enhancing inference speed. For effective structured pruning of LLMs, we highlight three critical elements that demand the utmost attention: formulating structured importance metrics, adaptively searching the global compressed model, and implementing compensation mechanisms to mitigate performance loss. First, FLAP determines whether the output feature map is easily recoverable when a column of weight is removed, based on the fluctuation pruning metric. Then it standardizes the importance scores to adaptively determine the global compressed model structure. At last, FLAP adds additional bias terms to recover the output feature maps using the baseline values. We thoroughly evaluate our approach on a variety of language benchmarks. Without any retraining, our method significantly outperforms the state-of-the-art methods, including LLM-Pruner and the extension of Wanda in structured pruning. The code is released at https://github.com/CASIA-IVA-Lab/FLAP.

PDF Details DOI