Author name cluster

Jinhao Li

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.

5 papers

1 author row

AAMAS Conference 2026 Conference Paper

Selective Amnesia: Observation Unlearning in Reinforcement Learning

Yue Yang
Jinhao Li
Hao Wang

Although the concept of machine unlearning has been widely explored in the past few years, unlearning in reinforcement learning (RL) models remains underdeveloped. In this paper, we undertake an in-depth exploration of reinforcement unlearning (RUL), a novel and challenging concept within the field of RL and machine unlearning. We investigate the inherent difficulties associated with RUL, pinpointing two critical factors that contribute to its complexity: agent-environment interactions and the sequential nature of decision-making. To tackle these challenges, we propose an unlearning algorithm that addresses the fundamentals of RUL from the perspective of environment observations, enabling observationlevel unlearning for both tabular and deep Q-learning. By quantitatively assessing the effects of observations through state-action values and modifying and retracing the policy trajectories establishedbytheoriginalmodel, wedemonstratethat, underreasonable assumptions, RUL can effectively eliminate both the immediate and subsequent impacts of the targeted unlearning observation. Empirical evaluations also validate the effectiveness of our RUL approach.

PDF

TMLR Journal 2026 Journal Article

Semantic-aware Adversarial Fine-tuning for CLIP

Jiacheng Zhang
Jinhao Li
Hanxun Huang
Sarah Monazam Erfani
Benjamin I. P. Rubinstein
Feng Liu

Recent studies have shown that CLIP model's adversarial robustness in zero-shot classification tasks can be enhanced by adversarially fine-tuning its image encoder with adversarial examples (AEs), which are generated by minimizing the cosine similarity between images and a hand-crafted template (e.g., ''A photo of a {label}''). However, it has been shown that the cosine similarity between a single image and a single hand-crafted template is insufficient to measure the similarity for image-text pairs. Building on this, in this paper, we find that the AEs generated using cosine similarity may fail to fool CLIP when the similarity metric is replaced with semantically enriched alternatives, making the image encoder fine-tuned with these AEs less robust. To overcome this issue, we first propose a semantic-ensemble attack to generate semantic-aware AEs by minimizing the average similarity between the original image and an ensemble of refined textual descriptions. These descriptions are initially generated by a foundation model to capture core semantic features beyond hand-crafted templates and are then refined to reduce hallucinations. To this end, we propose Semantic-aware Adversarial Fine-Tuning (SAFT), which fine-tunes CLIP's image encoder with semantic-aware AEs. Extensive experiments show that SAFT outperforms current methods, achieving substantial improvements in zero-shot adversarial robustness across 16 datasets. Our code is available at: https://github.com/tmlr-group/SAFT.

PDF Details

TMLR Journal 2025 Journal Article

Exploring Weak-to-Strong Generalization for CLIP-based Classification

Jinhao Li
Sarah Monazam Erfani
Lei Feng
James Bailey
Feng Liu

Aligning large-scale commercial models with user intent is crucial to preventing harmful outputs. Current methods rely on human supervision but become impractical as model complexity increases. When models surpass human knowledge, providing accurate feedback becomes challenging and inefficient. A novel solution proposed recently is using a weaker model to supervise a stronger model. This concept leverages the ability of weaker models to perform evaluations, thereby reducing the workload on human supervisors. Previous work has shown the effectiveness of weak-to-strong generalization in the context of language-only models. Extending this concept to vision-language models leverages these insights, adapting the proven benefits to a multi-modal context. In our study, we explore weak-to-strong generalization for CLIP-based classification. We propose a method, \emph{class prototype learning} (CPL), which aims to enhance the classification capabilities of the CLIP model, by learning more representative prototypes for each category. Our findings indicate that, despite using a simple loss function under weak supervision, CPL yields robust improvements in targeted scenarios, particularly when pretraining is limited. Extensive experiments demonstrate that our approach is effective under these settings, achieving a 3.67\% improvement over strong baseline methods.

PDF Details

NeurIPS Conference 2025 Conference Paper

Feature Unlearning: Theoretical Foundations and Practical Applications with Shuffling

Yue Yang
Jinhao Li
Hao Wang

Machine unlearning has become a focal point in recent research, yet the specific area of feature unlearning has not been thoroughly explored. Feature unlearning involves the elimination of specific features' effects from an already trained model, presenting distinct challenges that are still not comprehensively addressed. This paper presents a novel and straightforward approach to feature unlearning that employs a tactical shuffling of the features designated for removal. By redistributing the values of the features targeted for unlearning throughout the original training dataset and subsequently fine-tuning the model with this shuffled data, our proposed method provides a theoretical guarantee for effective feature unlearning. Under mild assumptions, our method can effectively disrupt the established correlations between unlearned features and the target outcomes, while preserving the relationships between the remaining features and the predicted outcomes. Our empirical studies across various datasets, validate that our approach not only successfully removes the effects of specified features but also maintains the informational integrity of the remaining features while achieving a faster convergence rate.

PDF Details

NeurIPS Conference 2024 Conference Paper

One-to-Multiple: A Progressive Style Transfer Unsupervised Domain-Adaptive Framework for Kidney Tumor Segmentation

Kai Hu
Jinhao Li
Yuan Zhang
Xiongjun Ye
Xieping Gao

In multi-sequence Magnetic Resonance Imaging (MRI), the accurate segmentation of the kidney and tumor based on traditional supervised methods typically necessitates detailed annotation for each sequence, which is both time-consuming and labor-intensive. Unsupervised Domain Adaptation (UDA) methods can effectively mitigate inter-domain differences by aligning cross-modal features, thereby reducing the annotation burden. However, most existing UDA methods are limited to one-to-one domain adaptation, which tends to be inefficient and resource-intensive when faced with multi-target domain transfer tasks. To address this challenge, we propose a novel and efficient One-to-Multiple Progressive Style Transfer Unsupervised Domain-Adaptive (PSTUDA) framework for kidney and tumor segmentation in multi-sequence MRI. Specifically, we develop a multi-level style dictionary to explicitly store the style information of each target domain at various stages, which alleviates the burden of a single generator in a multi-target transfer task and enables effective decoupling of content and style. Concurrently, we employ multiple cascading style fusion modules that utilize point-wise instance normalization to progressively recombine content and style features, which enhances cross-modal alignment and structural consistency. Experiments conducted on the private MSKT and public KiTS19 datasets demonstrate the superiority of the proposed PSTUDA over comparative methods in multi-sequence kidney and tumor segmentation. The average Dice Similarity Coefficients are increased by at least 1. 8% and 3. 9%, respectively. Impressively, our PSTUDA not only significantly reduces the floating-point computation by approximately 72% but also reduces the number of model parameters by about 50%, bringing higher efficiency and feasibility to practical clinical applications.

PDF Details DOI