Author name cluster

Lu Lin

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.

8 papers

2 author rows

ICML Conference 2025 Conference Paper

"Why Is There a Tumor? ": Tell Me the Reason, Show Me the Evidence

Mengmeng Ma 0002
Tang Li 0005
Yunxiang Peng 0002
Lu Lin
Volkan Beylergil
Binsheng Zhao
Oguz Akin
Xi Peng 0005

Medical AI models excel at tumor detection and segmentation. However, their latent representations often lack explicit ties to clinical semantics, producing outputs less trusted in clinical practice. Most of the existing models generate either segmentation masks/labels (localizing where without why) or textual justifications (explaining why without where), failing to ground clinical concepts in spatially localized evidence. To bridge this gap, we propose to develop models that can justify the segmentation or detection using clinically relevant terms and point to visual evidence. We address two core challenges: First, we curate a rationale dataset to tackle the lack of paired images, annotations, and textual rationales for training. The dataset includes 180K image-mask-rationale triples with quality evaluated by expert radiologists. Second, we design rationale-informed optimization that disentangles and localizes fine-grained clinical concepts in a self-supervised manner without requiring pixel-level concept annotations. Experiments across medical benchmarks show our model demonstrates superior performance in segmentation, detection, and beyond. The anonymous link to our code.

Details

YNIMG Journal 2025 Journal Article

Neural signatures and personalized neuromodulation in a subject experiencing context-dependent inhibitory control deficits

Layth S. Mattar
Shraddha Shah
Lily S. Chamakura
Denise Oswalt
Yue Zhang
Davin Devara
Jung Uk Kang
Zahra Jourahmad

The ability to override prepotent actions is critical to control impulses and adjust behavior depending on goals and contextual needs. In this study, we investigate the inhibitory control abilities of a patient diagnosed with Klüver-Bucy Syndrome following a left temporal resection. The patient presented with disruptive hypersexuality symptoms akin to compulsions, leading to the inability to control and suppress inappropriate actions. The patient was recruited for the current research study while undergoing intracranial monitoring for epilepsy, to investigate the cognitive and neural processes underlying the patient's inhibitory control symptoms. We formulated the hypothesis that a reactive inhibitory control deficit emerges in response to provocative triggers, and we designed a personalized paradigm pairing arousing images with a classic inhibitory control task. We not only confirmed disrupted performance following exposure to triggering, provocative material, but we also leveraged the simultaneously recorded neural data to identify a biomarker reflecting inhibitory control failures. Next, we repeated the experimental paradigm during and after personalized neuromodulation via direct high-frequency stimulation of the right inferior frontal cortex. The patient displayed a marked improvement in his behavior during neuromodulation, mirrored by changes in neural activity, spanning spectral features, event-related potentials and functional connectivity. Altogether, our study revealed that the patient's symptoms were not due to a global inhibition deficit, but to a specific control issue triggered by exposure to provocative material. Overall, our work showcases a feasible, effective approach towards data-driven personalized neuromodulation, which could be leveraged to mitigate specific inhibitory control deficits and potentially other symptoms of executive dysfunction.

Details DOI

NeurIPS Conference 2025 Conference Paper

Understanding and Rectifying Safety Perception Distortion in VLMs

Xiaohan Zou
Jian Kang
George Kesidis
Lu Lin

Recent studies reveal that vision-language models (VLMs) become more susceptible to harmful requests and jailbreak attacks after integrating the vision modality, exhibiting greater vulnerability than their text-only LLM backbones. To uncover the root cause of this phenomenon, we conduct an in-depth analysis and identify a key issue: multimodal inputs introduce an modality-induced activation shift toward a “safer” direction compared to their text-only counterparts, leading VLMs to systematically overestimate the safety of harmful inputs. We refer to this issue as safety perception distortion. To mitigate such distortion, we propose Activation Shift Disentanglement and Calibration (ShiftDC), a training-free method that decomposes and calibrates the modality-induced activation shift to reduce its impact on safety. By isolating and removing the safety-relevant component, ShiftDC restores the inherent safety alignment of the LLM backbone while preserving the vision-language capabilities of VLMs. Experiments demonstrate that ShiftDC significantly enhances safety alignment without impairing model utility.

PDF Details

NeurIPS Conference 2024 Conference Paper

Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization

Yuanpu Cao
Tianrong Zhang
Bochuan Cao
Ziyi Yin
Lu Lin
Fenglong Ma
Jinghui Chen

Researchers have been studying approaches to steer the behavior of Large Language Models (LLMs) and build personalized LLMs tailored for various applications. While fine-tuning seems to be a direct solution, it requires substantial computational resources and may significantly affect the utility of the original LLM. Recent endeavors have introduced more lightweight strategies, focusing on extracting ``steering vectors'' to guide the model's output toward desired behaviors by adjusting activations within specific layers of the LLM's transformer architecture. However, such steering vectors are directly extracted from the activations of human preference data and thus often lead to suboptimal results and occasional failures, especially in alignment-related scenarios. In this work, we propose an innovative approach that could produce more effective steering vectors through bi-directional preference optimization. Our method is designed to allow steering vectors to directly influence the generation probability of contrastive human preference data pairs, thereby offering a more precise representation of the target behavior. By carefully adjusting the direction and magnitude of the steering vector, we enabled personalized control over the desired behavior across a spectrum of intensities. Extensive experimentation across various open-ended generation tasks, particularly focusing on steering AI personas, has validated the efficacy of our approach. Moreover, we comprehensively investigate critical alignment-concerning scenarios, such as managing truthfulness, mitigating hallucination, and addressing jailbreaking attacks alongside their respective defenses. Remarkably, our method can still demonstrate outstanding steering effectiveness across these scenarios. Furthermore, we showcase the transferability of our steering vectors across different models/LoRAs and highlight the synergistic benefits of applying multiple vectors simultaneously. These findings significantly broaden the practicality and versatility of our proposed method.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

SCTrans: Multi-scale scRNA-seq Sub-vector Completion Transformer for Gene-selective Cell Type Annotation

Lu Lin
Wen Xue
Xindian Wei
Wenjun Shen
Cheng Liu
Si Wu
Hau San Wong

Cell type annotation is pivotal to single-cell RNA sequencing data (scRNA-seq)-based biological and medical analysis, e. g. , identifying biomarkers, exploring cellular heterogeneity, and understanding disease mechanisms. The previous annotation methods typically learn a nonlinear mapping to infer cell type from gene expression vectors, and thus fall short in discovering and associating salient genes with specific cell types. To address this issue, we propose a multi-scale scRNA-seq Sub-vector Completion Transformer, and our model is referred to as SCTrans. Considering that the expressiveness of gene sub-vectors is richer than that of individual genes, we perform multi-scale partitioning on gene vectors followed by masked sub-vector completion, conditioned on unmasked ones. Toward this end, the multi-scale sub-vectors are tokenized, and the intrinsic contextual relationships are modeled via self-attention computation and conditional contrastive regularization imposed on an encoding transformer. By performing mutual learning between the encoder and an additional lightweight counterpart, the salient tokens can be distinguished from the others. As a result, we can perform gene-selective cell type annotation, which contributes to our superior performance over state-of-the-art annotation methods.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

A3FL: Adversarially Adaptive Backdoor Attacks to Federated Learning

Hangfan Zhang
Jinyuan Jia
Jinghui Chen
Lu Lin
Dinghao Wu

Federated Learning (FL) is a distributed machine learning paradigm that allows multiple clients to train a global model collaboratively without sharing their local training data. Due to its distributed nature, many studies have shown that it is vulnerable to backdoor attacks. However, existing studies usually used a predetermined, fixed backdoor trigger or optimized it based solely on the local data and model without considering the global training dynamics. This leads to sub-optimal and less durable attack effectiveness, i. e. , their attack success rate is low when the attack budget is limited and decreases quickly if the attacker can no longer perform attacks anymore. To address these limitations, we propose A3FL, a new backdoor attack which adversarially adapts the backdoor trigger to make it less likely to be removed by the global training dynamics. Our key intuition is that the difference between the global model and the local model in FL makes the local-optimized trigger much less effective when transferred to the global model. We solve this by optimizing the trigger to even survive the worst-case scenario where the global model was trained to directly unlearn the trigger. Extensive experiments on benchmark datasets are conducted for twelve existing defenses to comprehensively evaluate the effectiveness of our A3FL. Our code is available at https: //github. com/hfzhang31/A3FL.

PDF Details

JMLR Journal 2019 Journal Article

Robust Estimation of Derivatives Using Locally Weighted Least Absolute Deviation Regression

Wenwu Wang
Ping Yu
Lu Lin
Tiejun Tong

In nonparametric regression, the derivative estimation has attracted much attention in recent years due to its wide applications. In this paper, we propose a new method for the derivative estimation using the locally weighted least absolute deviation regression. Different from the local polynomial regression, the proposed method does not require a finite variance for the error term and so is robust to the presence of heavy-tailed errors. Meanwhile, it does not require a zero median or a positive density at zero for the error term in comparison with the local median regression. We further show that the proposed estimator with random difference is asymptotically equivalent to the (infinitely) composite quantile regression estimator. In other words, running one regression is equivalent to combining infinitely many quantile regressions. In addition, the proposed method is also extended to estimate the derivatives at the boundaries and to estimate higher-order derivatives. For the equidistant design, we derive theoretical results for the proposed estimators, including the asymptotic bias and variance, consistency, and asymptotic normality. Finally, we conduct simulation studies to demonstrate that the proposed method has better performance than the existing methods in the presence of outliers and heavy-tailed errors, and analyze the Chinese house price data for the past ten years to illustrate the usefulness of the proposed method. [abs] [ pdf ][ bib ] &copy JMLR 2019. ( edit, beta )

PDF Details

JMLR Journal 2015 Journal Article

Derivative Estimation Based on Difference Sequence via Locally Weighted Least Squares Regression

Wenwu Wang
Lu Lin

A new method is proposed for estimating derivatives of a nonparametric regression function. By applying Taylor expansion technique to a derived symmetric difference sequence, we obtain a sequence of approximate linear regression representation in which the derivative is just the intercept term. Using locally weighted least squares, we estimate the derivative in the linear regression model. The estimator has less bias in both valleys and peaks of the true derivative function. For the special case of a domain with equispaced design points, the asymptotic bias and variance are derived; consistency and asymptotic normality are established. In simulations our estimators have less bias and mean square error than its main competitors, especially second order derivative estimator. [abs] [ pdf ][ bib ] &copy JMLR 2015. ( edit, beta )

PDF Details