Author name cluster

Yiming Liu

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.

13 papers

2 author rows

AAAI Conference 2026 Conference Paper

CIA: Cluster-Instance Alignment for Unsupervised Day-Night Vehicle Re-Identification

Yongguo Ling
Chen Zhang
Yiming Liu
Wenhao Shao

Cross-time vehicle re-identification (Re-ID), especially across day and night conditions, remains a challenging problem due to drastic illumination variations that lead to significant domain shifts. While existing methods perform well under daytime scenarios, their effectiveness degrades severely in cross-domain settings, and fully supervised solutions demand costly annotations in both domains. In this paper, we introduce a new setting, Unsupervised Day-Night Vehicle Re-Identification (USL-DN-ReID), and propose a novel Cluster-Instance Alignment (CIA) framework to address it. CIA performs dual-level alignment: 1) at the cluster level, a Dictionary-Guided Graph Matching (DGM) module builds a cross-domain topological graph using soft similarities among cluster centers and solves global matching via the Hungarian algorithm; 2) at the instance level, a Multi-Factor Adaptive Alignment (MAA) module introduces a multi-factor adaptive weighting strategy that emphasizes high-confidence pairwise relations while suppressing noise. Together, these components enable robust and scalable cross-domain adaptation without requiring target-domain labels. Extensive experiments conducted on the DN-348 and DN-Wild benchmarks demonstrate the effectiveness and superiority of the proposed CIA framework, setting new state-of-the-art results on both datasets.

PDF Details DOI

AAAI Conference 2026 Conference Paper

PLUM-Net: Prototype-Induced Label Structuring for Disentangled Multimodal Representation Network

Kehan Wang
Huan Zhao
Yong Wei
Xupeng Zha
Guanghui Ye
Cheng Zhu
Yiming Liu
Zixing Zhang

Existing multimodal representation learning approaches often rely on simple feature concatenation or unified transformations, which fail to effectively disentangle and leverage common and private information across different modalities in a progressive manner. Moreover, they typically lack adaptive modeling tailored to specific task requirements. To address these limitations, we propose a Prototype-Induced Label Structuring for Disentangled Multimodal Representation Network (PLUM-Net). It first employs a multilevel semantic alignment module to synchronize global and local semantics across audio, visual and textual streams. On this aligned foundation, a prototype-based single-modal label generation module derives modality-specific hard and soft-labels that subtly steer the network toward a cleaner split between shared and private cues. Guided by these labels, the task-conditioned feature bifurcator module channels information through the most beneficial common or private pathway for the given task, after which a private refinement module polishes and fuses each modality’s idiosyncratic signals. Extensive experiments show that PLUM-Net delivers strong performance on datasets such as CMU-MOSI, CMU-MOSEI and UR-FUNNY, achieving an ACC-2 of 90.3% on CMU-MOSI, representing a 2%–4% improvement over previous SOTA models.

PDF Details DOI

ICLR Conference 2025 Conference Paper

Can Watermarked LLMs be Identified by Users via Crafted Prompts?

Aiwei Liu
Sheng Guan
Yiming Liu
Leyi Pan
Yifei Zhang
Liancheng Fang
Lijie Wen 0001
Philip S. Yu

Text watermarking for Large Language Models (LLMs) has made significant progress in detecting LLM outputs and preventing misuse. Current watermarking techniques offer high detectability, minimal impact on text quality, and robustness to text editing. However, current researches lack investigation into the imperceptibility of watermarking techniques in LLM services. This is crucial as LLM providers may not want to disclose the presence of watermarks in real-world scenarios, as it could reduce user willingness to use the service and make watermarks more vulnerable to attacks. This work is the first to investigate the imperceptibility of watermarked LLMs. We design an identification algorithm called Water-Probe that detects watermarks through well-designed prompts to the LLM. Our key motivation is that current watermarked LLMs expose consistent biases under the same watermark key, resulting in similar differences across prompts under different watermark keys. Experiments show that almost all mainstream watermarking algorithms are easily identified with our well-designed prompts, while Water-Probe demonstrates a minimal false positive rate for non-watermarked LLMs. Finally, we propose that the key to enhancing the imperceptibility of watermarked LLMs is to increase the randomness of watermark key selection. Based on this, we introduce the Water-Bag strategy, which significantly improves watermark imperceptibility by merging multiple watermark keys.

Details

JBHI Journal 2025 Journal Article

NRAG: A Knowledge-Enhanced LLM Framework for Interpretable Neurosurgical Disease Diagnosis in Outpatient and Emergency Settings

Haoyu Tian
Yiming Liu
Xinyu Dai
Xin Dong
Jian Yu
Wei Wei
Boran Wang
Xuezhong Zhou

Large language models (LLMs) have achieved state-of-the-art performance in numerous domains, yet their clinical deployment faces critical barriers, particularly insufficient reasoning in complex scenarios and limited interpretability. These challenges are exacerbated in neurosurgical diagnosis for outpatient and emergency settings, where time-sensitive decision-making, fragmented data, and complex comorbidities render conventional free-text-based modeling approaches unreliable. To address the limitations of existing LLMs in medical auxiliary diagnosis, particularly in interpretability and predictive performance, this study proposed NRAG, an auxiliary diagnosis method that combines LLMs with knowledge graphs (KGs). It extracts symptom descriptions from clinical records and performs personalized retrieval of associated paths in KG, and supplements potential patient symptoms to optimize the diagnosis model. Comparative experiments involving multiple general-domain and medical-domain LLMs, along with case studies, were conducted to validate the NRAG's effectiveness. Experimental results demonstrate that integrating KG significantly improves diagnosis accuracy, achieving an F1-score of 0. 8150. It also substantially improves model interpretability and performs excellently in expert evaluations. Ablation studies and comparative experiments with other general-domain and medical-domain LLMs confirm the superior performance of the proposed NRAG. NRAG effectively supplements missing symptom information and provides knowledge-path-based evidence for diagnosis results, while improving the precision and interpretability of intelligent diagnosis. Furthermore, this approach sets the foundation for intelligent diagnoses in neurosurgery while providing a methodological framework for the integration of in-depth clinical data mining with medical knowledge base resources.

Details DOI

ICLR Conference 2025 Conference Paper

Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective

Yiming Liu
Kezhao Liu
Yao Xiao
Ziyi Dong
Xiaogang Xu 0002
Pengxu Wei
Liang Lin

Diffusion-Based Purification (DBP) has emerged as an effective defense mechanism against adversarial attacks. The success of DBP is often attributed to the forward diffusion process, which reduces the distribution gap between clean and adversarial images by adding Gaussian noise. Although this explanation is theoretically grounded, the precise contribution of this process to robustness remains unclear. In this paper, through a systematic investigation, we propose that the intrinsic stochasticity in the DBP procedure is the primary factor driving robustness. To explore this hypothesis, we introduce a novel Deterministic White-Box (DW-box) evaluation protocol to assess robustness in the absence of stochasticity, and analyze attack trajectories and loss landscapes. Our results suggest that DBP models primarily leverage stochasticity to evade effective attack directions, and that their ability to purify adversarial perturbations can be weak. To further enhance the robustness of DBP models, we propose Adversarial Denoising Diffusion Training (ADDT), which incorporates classifier-guided adversarial perturbations into diffusion training, thereby strengthening the models' ability to purify adversarial perturbations. Additionally, we propose Rank-Based Gaussian Mapping (RBGM) to improve the compatibility of perturbations with diffusion models. Experimental results validate the effectiveness of ADDT. In conclusion, our study suggests that future research on DBP can benefit from the perspective of decoupling stochasticity-based and purification-based robustness.

Details

NeurIPS Conference 2024 Conference Paper

Benchmarking Complex Instruction-Following with Multiple Constraints Composition

Bosi Wen
Pei Ke
Xiaotao Gu
Lindong Wu
Hao Huang
Jinfeng Zhou
Wenchuang Li
Binxin Hu

Instruction following is one of the fundamental capabilities of large language models (LLMs). As the ability of LLMs is constantly improving, they have been increasingly applied to deal with complex human instructions in real-world scenarios. Therefore, how to evaluate the ability of complex instruction-following of LLMs has become a critical research problem. Existing benchmarks mainly focus on modeling different types of constraints in human instructions while neglecting the composition of different constraints, which is an indispensable constituent in complex instructions. To this end, we propose ComplexBench, a benchmark for comprehensively evaluating the ability of LLMs to follow complex instructions composed of multiple constraints. We propose a hierarchical taxonomy for complex instructions, including 4 constraint types, 19 constraint dimensions, and 4 composition types, and manually collect a high-quality dataset accordingly. To make the evaluation reliable, we augment LLM-based evaluators with rules to effectively verify whether generated texts can satisfy each constraint and composition. Furthermore, we obtain the final evaluation score based on the dependency structure determined by different composition types. ComplexBench identifies significant deficiencies in existing LLMs when dealing with complex instructions with multiple constraints composition.

PDF Details DOI

JBHI Journal 2024 Journal Article

Multi-Modal Multi-Slice Cooperative Dual-Domain Cascaded De-Aliasing Network for MR Imaging Reconstruction

Xuebin Sun
Yanwei Pang
Yiming Liu
Caifeng Shan
Shing Shin Cheng

Recent advancements in Magnetic Resonance Imaging (MRI) reconstruction techniques aim to accelerate the imaging process. However, these methods still face two key limitations. Firstly, although the same location consistently provides anatomical information across different modalities, such as organs, tissues, or lesions, previous studies have predominantly relied on single-modality information, overlooking the potential advantages of incorporating complementary data from other modalities. Secondly, while adjacent MRI slices often capture the same location or organ with similar anatomical structures, only a few methods consider the information from neighboring slices during the reconstruction process. To address these challenges, we propose a M ulti-modal M ulti-slice cooperative D ual-domain cascaded de-alising network for MR imaging R econstruction (MMDR). Specifically, we design a multi-slice and multi-modal feature fusion network based on 3D convolution and swin transformer that efficiently extracts multi-modal features from MRI. Then, a dual domain cascaded recurrent network through dense-blocks with large receptive fields for fast MRI reconstruction is explored. Extensive experiments on the IXI datasets were carried out to evaluate the proposed method's robustness across varying network structures, under-sampling rates, and sampling patterns. MMDR demonstrates promising performance across both qualitative and quantitative metrics, particularly with a competitive PSNE of 42. 15 and an SSIM of 0. 984 for T2 reconstruction using 30% T2WI and PDWI, as well as achieving a PSNE of 39. 92 and an SSIM of 0. 966 for PDWI reconstruction with 30% PDWI and T2WI.

Details DOI

AAAI Conference 2023 Conference Paper

Intriguing Findings of Frequency Selection for Image Deblurring

Xintian Mao
Yiming Liu
Fengze Liu
Qingli Li
Wei Shen
Yan Wang

Blur was naturally analyzed in the frequency domain, by estimating the latent sharp image and the blur kernel given a blurry image. Recent progress on image deblurring always designs end-to-end architectures and aims at learning the difference between blurry and sharp image pairs from pixel-level, which inevitably overlooks the importance of blur kernels. This paper reveals an intriguing phenomenon that simply applying ReLU operation on the frequency domain of a blur image followed by inverse Fourier transform, i.e., frequency selection, provides faithful information about the blur pattern (e.g., the blur direction and blur level, implicitly shows the kernel pattern). Based on this observation, we attempt to leverage kernel-level information for image deblurring networks by inserting Fourier transform, ReLU operation, and inverse Fourier transform to the standard ResBlock. 1 × 1 convolution is further added to let the network modulate flexible thresholds for frequency selection. We term our newly built block as Res FFT-ReLU Block, which takes advantages of both kernel-level and pixel-level features via learning frequency-spatial dual-domain representations. Extensive experiments are conducted to acquire a thorough analysis on the insights of the method. Moreover, after plugging the proposed block into NAFNet, we can achieve 33.85 dB in PSNR on GoPro dataset. Our method noticeably improves backbone architectures without introducing many parameters, while maintaining low computational complexity. Code is available at https://github.com/DeepMed-Lab/DeepRFT-AAAI2023.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

On-the-Fly Adapting Code Summarization on Trainable Cost-Effective Language Models

Yufan Cai
Yun Lin
Chenyan Liu
Jinglian Wu
Yifan Zhang
Yiming Liu
Yeyun Gong
Jin Song Dong

Deep learning models are emerging to summarize source code to comment, facilitating tasks of code documentation and program comprehension. Scaled-up large language models trained on large open corpus have achieved good performance in such tasks. However, in practice, the subject code in one certain project can be specific, which may not align with the overall training corpus. Some code samples from other projects may be contradictory and introduce inconsistencies when the models try to fit all the samples. In this work, we introduce a novel approach, Adacom, to improve the performance of comment generators by on-the-fly model adaptation. This research is motivated by the observation that deep comment generators often need to strike a balance as they need to fit all the training samples. Specifically, for one certain target code $c$, some training samples $S_p$ could have made more contributions while other samples $S_o$ could have counter effects. However, the traditional fine-tuned models need to fit both $S_p$ and $S_o$ from a global perspective, leading to compromised performance for one certain target code $c$. In this context, we design Adacom to (1) detect whether the model might have a compromised performance on a target code $c$ and (2) retrieve a few helpful training samples $S_p$ that have contradictory samples in the training dataset and, (3) adapt the model on the fly by re-training the $S_p$ to strengthen the helpful samples and unlearn the harmful samples. Our extensive experiments on 7 comment generators and 4 public datasets show that (1) can significantly boost the performance of comment generation (BLEU4 score by on average 14. 9\%, METEOR by 12. 2\%, and ROUGE-L by 7. 4\%), (2) the adaptation on one code sample is cost-effective and acceptable as an on-the-fly solution, and (3) can adapt well on out-of-distribution code samples.

PDF Details

AAAI Conference 2022 System Paper

FORCE: A Framework of Rule-Based Conversational Recommender System

Jun Quan
Ze Wei
Qiang Gan
Jingqi Yao
Jingyi Lu
Yuchen Dong
Yiming Liu
Yi Zeng

The conversational recommender systems (CRSs) have received extensive attention in recent years. However, most of the existing works focus on various deep learning models, which are largely limited by the requirement of large-scale human-annotated datasets. Such methods are not able to deal with the cold-start scenarios in industrial products. To alleviate the problem, we propose FORCE, a Framework Of Rulebased Conversational rEcommender system that helps developers to quickly build CRS bots by simple configuration. We conduct experiments on two datasets in different languages and domains to verify its effectiveness and usability.

PDF Details

AAAI Conference 2021 System Paper

Integrating Pre-trained Model into Rule-based Dialogue Management

Jun Quan
Meng Yang
Qiang Gan
Deyi Xiong
Yiming Liu
Yuchen Dong
Fangxin Ouyang
Jun Tian

Rule-based dialogue management is still the most popular solution for industrial task-oriented dialogue systems for their interpretablility. However, it is hard for developers to maintain the dialogue logic when the scenarios get more and more complex. On the other hand, data-driven dialogue systems, usually with end-to-end structures, are popular in academic research and easier to deal with complex conversations, but such methods require plenty of training data and the behaviors are less interpretable. In this paper, we propose a method to leverages the strength of both rule-based and data-driven dialogue managers (DM). We firstly introduce the DM of Carina Dialog System (CDS, an advanced industrial dialogue system built by Microsoft). Then we propose the “modeltrigger” design to make the DM trainable thus scalable to scenario changes. Furthermore, we integrate pre-trained models and empower the DM with few-shot capability. The experimental results demonstrate the effectiveness and strong fewshot capability of our method.

PDF Details

ICRA Conference 2010 Conference Paper

Scene understanding in a large dynamic environment through a laser-based sensing

Huijing Zhao
Yiming Liu
Xiaolong Zhu
Yipu Zhao
Hongbin Zha

It became a well known technology that a map of complex environment containing low-level geometric primitives (such as laser points) can be generated using a robot with laser scanners. This research is motivated by the need of obtaining semantic knowledge of a large urban outdoor environment after the robot explores and generates a low-level sensing data set. An algorithm is developed with the data represented in a range image, while each pixel can be converted into a 3D coordinate. Using an existing segmentation method that models only geometric homogeneities, the data of a single object of complex geometry, such as people, cars, trees etc. , is partitioned into different segments. Such a segmentation result will greatly restrict the capability of object recognition. This research proposes a framework of simultaneous segmentation and classification of range image, where the classification of each segment is conducted based on its geometric properties, and homogeneity of each segment is evaluated conditioned on each object class. Experiments are presented using the data of a large dynamic urban outdoor environment, and performance of the algorithm is evaluated.

Details

IROS Conference 2010 Conference Paper

Segmentation and classification of range image from an intelligent vehicle in urban environment

Xiaolong Zhu
Huijing Zhao
Yiming Liu
Yipu Zhao
Hongbin Zha

As the rapid development of sensing and mapping techniques, it becomes a well-known technology that a map of complex environment can be generated using a robot carrying sensors. However, most of the existing researches represent environments directly using the integration of point clouds or other low-level geometric primitives. It remains an open problem to automatically convert these low-level map representations to semantic descriptions in order to effectively support high-level decision of a robot. Based on another representation of 3D point clouds, i. e. range image, this paper proposes a framework of segmentation and classification of range image, the objective of which is to annotate class labels to the data clusters that are obtained through a graph-based segmentation. Experimental results are presented and evaluated demonstrating that the proposed algorithm has efficiency in understanding the semantic knowledge of a large dynamic urban outdoor environment.

Details