58 citations · 101 across the 18 of their papers we have counts for
20 papers
Counterfactual Regret for Reflective Agents with Lean-Verified Guarantees
Zhongnian Li, Shi Xu, Mengting Xu +2
Reflective language agents reuse feedback and memory to adapt across tasks without updating model weights. However, existing guarantees for policy selection and action generation d…
Think in Strategies, Act with Tools: Traceable Agentic Optimization for Combinatorial Problems
Zhongnian Li, Shi Xu, Peng Ying +3
Optimization by PROmpting (OPRO) directly leverages Large Language Models (LLMs) to generate candidate solutions through natural-language prompting. However, OPRO's optimization pr…
One Shared LoRA Weight for MRI Reconstruction across Acceleration Factors
Zhiwei Zhao, Weikang Gong, Zhongnian Li +1
Accelerated MRI reconstruction recovers images from undersampled k-space. However, different acceleration factors produce distinct artifact patterns. Existing methods often train s…
Selectivity Matters: Source Node Influence Pruning for Unsupervised Graph Domain Adaptation
Ridong Han, Yawen Shen, Zhongnian Li +3
Unsupervised Graph Domain Adaptation (UGDA) aims to facilitate knowledge transfer from a labeled source graph to an unlabeled target graph by mitigating cross-domain distribution s…
CoDe-R: Refining Decompiler Output with LLMs via Rationale Guidance and Adaptive Inference
Qiang Zhang, Zhongnian Li
Binary decompilation is a critical reverse engineering task aimed at reconstructing high-level source code from stripped executables. Although Large Language Models (LLMs) have rec…
Deep Learning Based Joint Channel Estimation and Positioning for Sparse XL-MIMO OFDM Systems
Zhongnian Li, Chao Zheng, Jian Xiao +4
This paper investigates joint channel estimation and positioning in near-field sparse extra-large multiple-input multiple-output (XL-MIMO) orthogonal frequency division multiplexin…
Learning from True-False Labels via Multi-modal Prompt Retrieving
Zhongnian Li, Jinghao Xu, Peng Ying +2
Pre-trained Vision-Language Models (VLMs) exhibit strong zero-shot classification abilities, demonstrating great potential for generating weakly supervised labels. Unfortunately, e…
Determined Multi-Label Learning via Similarity-Based Prompt
Meng Wei, Zhongnian Li, Peng Ying +2
In multi-label classification, each training instance is associated with multiple class labels simultaneously. Unfortunately, collecting the fully precise class labels for each tra…
Learning from Reduced Labels for Long-Tailed Data
Meng Wei, Zhongnian Li, Yong Zhou +1
Long-tailed data is prevalent in real-world classification tasks and heavily relies on supervised information, which makes the annotation process exceptionally labor-intensive and…
Multi-label Learning from Privacy-Label
Zhongnian Li, Haotian Ren, Tongfeng Sun +1
Multi-abel Learning (MLL) often involves the assignment of multiple relevant labels to each instance, which can lead to the leakage of sensitive information (such as smoking, disea…
Learning from Stochastic Labels
Meng Wei, Zhongnian Li, Yong Zhou +2
Annotating multi-class instances is a crucial task in the field of machine learning. Unfortunately, identifying the correct class label from a long sequence of candidate labels is…
Complementary Labels Learning with Augmented Classes
Zhongnian Li, Jian Zhang, Mengting Xu +2
Complementary Labels Learning (CLL) arises in many real-world tasks such as private questions classification and online learning, which aims to alleviate the annotation cost compar…
Class-Imbalanced Complementary-Label Learning via Weighted Loss
Meng Wei, Yong Zhou, Zhongnian Li +1
Complementary-label learning (CLL) is widely used in weakly supervised classification, but it faces a significant challenge in real-world datasets when confronted with class-imbala…
Learning from Positive and Unlabeled Data with Augmented Classes
Zhongnian Li, Liutao Yang, Zhongchen Ma +3
Positive Unlabeled (PU) learning aims to learn a binary classifier from only positive and unlabeled data, which is utilized in many real-world scenarios. However, existing PU learn…
InfoAT: Improving Adversarial Training Using the Information Bottleneck Principle
Mengting Xu, Tao Zhang, Zhongnian Li +1
Adversarial training (AT) has shown excellent high performance in defending against adversarial examples. Recent studies demonstrate that examples are not equally important to the…
Low-Dose CT Denoising via Sinogram Inner-Structure Transformer
Liutao Yang, Zhongnian Li, Rongjun Ge +3
Low-Dose Computed Tomography (LDCT) technique, which reduces the radiation harm to human bodies, is now attracting increasing interest in the medical imaging field. As the image qu…
Scale-Invariant Adversarial Attack for Evaluating and Enhancing Adversarial Defenses
Mengting Xu, Tao Zhang, Zhongnian Li +1
Efficient and effective attacks are crucial for reliable evaluation of defenses, and also for developing robust models. Projected Gradient Descent (PGD) attack has been demonstrate…
Towards Evaluating the Robustness of Deep Diagnostic Models by Adversarial Attack
Mengting Xu, Tao Zhang, Zhongnian Li +2
Deep learning models (with neural networks) have been widely used in challenging tasks such as computer-aided disease diagnosis based on medical images. Recent studies have shown d…
Improving the Certified Robustness of Neural Networks via Consistency Regularization
Mengting Xu, Tao Zhang, Zhongnian Li +1
A range of defense methods have been proposed to improve the robustness of neural networks on adversarial examples, among which provable defense methods have been demonstrated to b…
SEGAN: Structure-Enhanced Generative Adversarial Network for Compressed Sensing MRI Reconstruction
Zhongnian Li, Tao Zhang, Peng Wan +1
Generative Adversarial Networks (GANs) are powerful tools for reconstructing Compressed Sensing Magnetic Resonance Imaging (CS-MRI). However most recent works lack exploration of s…