papers

Publications (368)

cs.LG2026

LLM Unlearning with LLM Beliefs

Kemou Li, Qizhou Wang, Yue Wang +4

Large language models trained on vast corpora inherently risk memorizing sensitive or harmful content, which may later resurface in their outputs. Prevailing unlearning methods gen…

cs.CV2026

Transferability of Adversarial Attacks in Video-based MLLMs: A Cross-modal Image-to-Video Approach

Linhao Huang, Xue Jiang, Zhiqiang Wang +5

Video-based multimodal large language models (V-MLLMs) have shown vulnerability to adversarial examples in video-text multimodal tasks. However, the transferability of adversarial…

cond-mat.mes-hall2024

Revealing dark exciton signatures in polariton spectra of 2D materials

Beatriz Ferreira, Hangyong Shan, Roberto Rosati +12

Dark excitons in transition metal dichalcogenides (TMD) have been so far neglected in the context of polariton physics due to their lack of oscillator strength. However, in tungste…

cs.LG2021

Learning Diverse-Structured Networks for Adversarial Robustness

Xuefeng Du, Jingfeng Zhang, Bo Han +5

In adversarial training (AT), the main focus has been the objective and optimizer while the model has been less studied, so that the models being used are still those classic ones…

cs.LG2025

FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learning

Zhiqin Yang, Yonggang Zhang, Chenxin Li +3

Federated Learning (FL) confronts a significant challenge known as data heterogeneity, which impairs model performance and convergence. Existing methods have made notable progress…

cs.CV2023

Towards Efficient Task-Driven Model Reprogramming with Foundation Models

Shoukai Xu, Jiangchao Yao, Ran Luo +5

Vision foundation models exhibit impressive power, benefiting from the extremely large model capacity and broad training data. However, in practice, downstream scenarios may only s…

cs.CV2026

Reflective Flow Sampling Enhancement

Zikai Zhou, Muyao Wang, Shitong Shao +4

The growing demand for text-to-image generation has led to rapid advances in generative modeling. Recently, text-to-image diffusion models trained with flow matching algorithms, su…

cs.LG2024

Enhancing Neural Subset Selection: Integrating Background Information into Set Representations

Binghui Xie, Yatao Bian, Kaiwen zhou +5

Learning neural subset selection tasks, such as compound selection in AI-aided drug discovery, have become increasingly pivotal across diverse applications. The existing methodolog…

cond-mat.str-el2019

A non-Abelian twist to integer quantum Hall states

Pedro L. S. Lopes, V. L. Quito, Bo Han +1

Through a theoretical coupled wire model, we construct strongly correlated electronic \emph{integer} quantum Hall states. As a distinguishing feature, these states support electric…

cs.LG2023

InstanT: Semi-supervised Learning with Instance-dependent Thresholds

Muyang Li, Runze Wu, Haoyu Liu +4

Semi-supervised learning (SSL) has been a fundamental challenge in machine learning for decades. The primary family of SSL algorithms, known as pseudo-labeling, involves assigning…

cs.LG2023

A Universal Unbiased Method for Classification from Aggregate Observations

Zixi Wei, Lei Feng, Bo Han +4

In conventional supervised classification, true labels are required for individual instances. However, it could be prohibitive to collect the true labels for individual instances,…

cs.HC2026

Exploring Collaborative Immersive Visualization & Analytics for High-Dimensional Scientific Data through Domain Expert Perspectives

Fahim Arsad Nafis, Jie Li, Simon Su +2

Cross-disciplinary teams increasingly work with high-dimensional scientific datasets, yet fragmented toolchains and limited support for shared exploration hinder collaboration. Pri…

cs.CL2025

Weak-to-Strong GraphRAG: Aligning Weak Retrievers with Large Language Models for Graph-based Retrieval Augmented Generation

Deyu Zou, Yongqiang Chen, Mufei Li +5

Graph-based retrieval-augmented generation (RAG) enables large language models (LLMs) to ground responses with structured external knowledge from up-to-date knowledge graphs (KGs)…

cond-mat.mtrl-sci2024

Precise structure and polarization determination of Hf0.5Zr0.5O2 with electron ptychography

Xiaoyue Gao1, Zhuohui Liu, Bo Han +8

Hf0.5Zr0.5O2 (HZO) is a promising candidate for next generation ferroelectric memories and transistors. However, its ferroelectricity origin is still under debate due to the comple…

q-bio.QM2025

Atomas: Hierarchical Alignment on Molecule-Text for Unified Molecule Understanding and Generation

Yikun Zhang, Geyan Ye, Chaohao Yuan +5

Molecule-and-text cross-modal representation learning has emerged as a promising direction for enhancing the quality of molecular representation, thereby improving performance in v…

cs.LG2021

Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels

Songhua Wu, Xiaobo Xia, Tongliang Liu +5

Learning with noisy labels has attracted a lot of attention in recent years, where the mainstream approaches are in pointwise manners. Meanwhile, pairwise manners have shown great…

cs.CV2025

Epistemic Uncertainty for Generated Image Detection

Jun Nie, Yonggang Zhang, Tongliang Liu +3

We introduce a novel framework for AI-generated image detection through epistemic uncertainty, aiming to address critical security concerns in the era of generative models. Our key…

cs.LG2025

Understanding and Enhancing the Transferability of Jailbreaking Attacks

Runqi Lin, Bo Han, Fengwang Li +1

Jailbreaking attacks can effectively manipulate open-source large language models (LLMs) to produce harmful responses. However, these attacks exhibit limited transferability, faili…

cs.CV2014

HSR: L1/2 Regularized Sparse Representation for Fast Face Recognition using Hierarchical Feature Selection

Bo Han, Bo He, Tingting Sun +2

In this paper, we propose a novel method for fast face recognition called L1/2 Regularized Sparse Representation using Hierarchical Feature Selection (HSR). By employing hierarchic…

cs.LG2026

When and Why Does Multi-Agent Debate Fail and Does It Really Underperform?

Yongqiang Chen, Gang Niu, James Cheng +2

The paper examines why multi-agent debate (MAD) often underperforms single-agent methods, identifies flaws in existing competitive and consensus-based MAD protocols, and proposes a…

#multi-agent systems#large language models#debate protocols#game theory
cs.LG2023

On Strengthening and Defending Graph Reconstruction Attack with Markov Chain Approximation

Zhanke Zhou, Chenyu Zhou, Xuan Li +3

Although powerful graph neural networks (GNNs) have boosted numerous real-world applications, the potential privacy risk is still underexplored. To close this gap, we perform the f…

cs.LG2022

Rethinking Class-Prior Estimation for Positive-Unlabeled Learning

Yu Yao, Tongliang Liu, Bo Han +4

Given only positive (P) and unlabeled (U) data, PU learning can train a binary classifier without any negative data. It has two building blocks: PU class-prior estimation (CPE) and…

cs.CL2026

Hidden Human-Like Nature of Machine-Generated Texts: Theory and Detection Enhancement

Chenwang Wu, Yiu-ming Cheung, Bo Han +1

Machine-generated texts (MGTs) produced by large language models (LLMs) are increasingly prevalent across various applications, while their potential misuse in fake news propagatio…

cs.LG2023

Noise-robust Graph Learning by Estimating and Leveraging Pairwise Interactions

Xuefeng Du, Tian Bian, Yu Rong +6

Teaching Graph Neural Networks (GNNs) to accurately classify nodes under severely noisy labels is an important problem in real-world graph learning applications, but is currently u…

cs.LG2026

TriSpec: Ternary Speculative Decoding via Lightweight Proxy Verification

Haoyun Jiang, Junqi He, Feng Hong +8

Inference efficiency in Large Language Models (LLMs) is fundamentally limited by their serial, autoregressive generation, especially as reasoning becomes a key capability and respo…

cs.LG2023

Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability

Jianing Zhu, Hengzhuang Li, Jiangchao Yao +3

Out-of-distribution (OOD) detection is an indispensable aspect of secure AI when deploying machine learning models in real-world applications. Previous paradigms either explore bet…

cs.LG2023

Combating Representation Learning Disparity with Geometric Harmonization

Zhihan Zhou, Jiangchao Yao, Feng Hong +3

Self-supervised learning (SSL) as an effective paradigm of representation learning has achieved tremendous success on various curated datasets in diverse scenarios. Nevertheless, w…

cs.NI2023

Will Metaverse be NextG Internet? Vision, Hype, and Reality

Ruizhi Cheng, Nan Wu, Songqing Chen +1

Metaverse, with the combination of the prefix "meta" (meaning transcending) and the word "universe", has been deemed as the next-generation (NextG) Internet. It aims to create a sh…

cs.LG2026

Per-parameter Task Arithmetic for Unlearning in Large Language Models

Chengyi Cai, Zesheng Ye, Jiangchao Yao +5

In large language model (LLM) unlearning, private information is required to be removed. Task arithmetic unlearns by subtracting a specific task vector (TV)--defined as the paramet…

cs.AI2026

AlphaApollo: A System for Deep Agentic Reasoning

Zhanke Zhou, Chentao Cao, Xiao Feng +15

We present AlphaApollo, an agentic reasoning system that targets two bottlenecks in foundation-model reasoning: (1) limited reasoning capacity for complex, long-horizon problem sol…

cs.LG2024

Efficient Private SCO for Heavy-Tailed Data via Averaged Clipping

Chenhan Jin, Kaiwen Zhou, Bo Han +2

We consider stochastic convex optimization for heavy-tailed data with the guarantee of being differentially private (DP). Most prior works on differentially private stochastic conv…

cs.LG2025

From Debate to Equilibrium: Belief-Driven Multi-Agent LLM Reasoning via Bayesian Nash Equilibrium

Xie Yi, Zhanke Zhou, Chentao Cao +3

Multi-agent frameworks can substantially boost the reasoning power of large language models (LLMs), but they typically incur heavy computational costs and lack convergence guarante…

cs.LG2023

Label-Noise Learning with Intrinsically Long-Tailed Data

Yang Lu, Yiliang Zhang, Bo Han +2

Label noise is one of the key factors that lead to the poor generalization of deep learning models. Existing label-noise learning methods usually assume that the ground-truth class…

cs.LG2023

AdaProp: Learning Adaptive Propagation for Graph Neural Network based Knowledge Graph Reasoning

Yongqi Zhang, Zhanke Zhou, Quanming Yao +2

Due to the popularity of Graph Neural Networks (GNNs), various GNN-based methods have been designed to reason on knowledge graphs (KGs). An important design component of GNN-based…

cs.LG2019

SUM: Suboptimal Unitary Multi-task Learning Framework for Spatiotemporal Data Prediction

Qichen Li, Jiaxin Pei, Jianding Zhang +1

The typical multi-task learning methods for spatio-temporal data prediction involve low-rank tensor computation. However, such a method have relatively weak performance when the ta…

cs.LG2025

One-shot Federated Learning Methods: A Practical Guide

Xiang Liu, Zhenheng Tang, Xia Li +6

One-shot Federated Learning (OFL) is a distributed machine learning paradigm that constrains client-server communication to a single round, addressing privacy and communication ove…

math.DS2023

Centralizer of fixed point free separating flows

Bo Han, Xiao Wen

In this paper, we study the centralizer of a separating continuous flow without fixed points. We show that if is a compact metric space and is a separating flow w…

cs.LG2024

Unraveling the Impact of Heterophilic Structures on Graph Positive-Unlabeled Learning

Yuhao Wu, Jiangchao Yao, Bo Han +2

While Positive-Unlabeled (PU) learning is vital in many real-world scenarios, its application to graph data still remains under-explored. We unveil that a critical challenge for PU…

cs.LG2024

How Interpretable Are Interpretable Graph Neural Networks?

Yongqiang Chen, Yatao Bian, Bo Han +1

Interpretable graph neural networks (XGNNs ) are widely adopted in various scientific applications involving graph-structured data. Existing XGNNs predominantly adopt the attention…

cs.CV2022

Contrastive Learning with Boosted Memorization

Zhihan Zhou, Jiangchao Yao, Yanfeng Wang +2

Self-supervised learning has achieved a great success in the representation learning of visual and textual data. However, the current methods are mainly validated on the well-curat…

cs.LG2021

A Survey of Label-noise Representation Learning: Past, Present and Future

Bo Han, Quanming Yao, Tongliang Liu +4

Classical machine learning implicitly assumes that labels of the training data are sampled from a clean distribution, which can be too restrictive for real-world scenarios. However…

cs.LG2019

Where is the Bottleneck of Adversarial Learning with Unlabeled Data?

Jingfeng Zhang, Bo Han, Gang Niu +2

Deep neural networks (DNNs) are incredibly brittle due to adversarial examples. To robustify DNNs, adversarial training was proposed, which requires large-scale but well-labeled da…

cs.LG2023

FlatMatch: Bridging Labeled Data and Unlabeled Data with Cross-Sharpness for Semi-Supervised Learning

Zhuo Huang, Li Shen, Jun Yu +2

Semi-Supervised Learning (SSL) has been an effective way to leverage abundant unlabeled data with extremely scarce labeled data. However, most SSL methods are commonly based on ins…

cs.CL2026

CausalGame: Benchmarking Causal Thinking of LLM Agents in Games

Zhenhao Chen, Yongqiang Chen, Chenxi Liu +7

Building AI Scientist agents with Large Language Models (LLMs) has recently attracted growing attention. Since scientific discovery fundamentally relies on uncovering causal relati…

cs.LG2024

Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection

Chentao Cao, Zhun Zhong, Zhanke Zhou +3

Detecting out-of-distribution (OOD) samples is essential when deploying machine learning models in open-world scenarios. Zero-shot OOD detection, requiring no training on in-distri…

cs.CL2026

Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory

Jingwei Sun, Jianing Zhu, Jiangchao Yao +2

To enable reliable long-term interaction, LLM agents require a memory system that can faithfully store, efficiently retrieve, and deeply reason over accumulated dialogue history. M…

cs.LG2023

Positional Information Matters for Invariant In-Context Learning: A Case Study of Simple Function Classes

Yongqiang Chen, Binghui Xie, Kaiwen Zhou +3

In-context learning (ICL) refers to the ability of a model to condition on a few in-context demonstrations (input-output examples of the underlying task) to generate the answer for…

cond-mat.mes-hall2021

Torsion, energy magnetization and thermal Hall effect

Ze-Min Huang, Bo Han, Xiao-Qi Sun

We study the effective action of hydrostatic response to torsion in the absence of spin connections in gapped -dimensional topological phases. In previous studies…

cs.LG2026

BrokenBind: Universal Modality Exploration beyond Dataset Boundaries

Zhuo Huang, Runnan Chen, Bo Han +3

Multi-modal learning combines various modalities to provide a comprehensive understanding of real-world problems. A common strategy is to directly bind different modalities togethe…

cond-mat.supr-con2025

Resolving Phonons in Superconductor Bi2Sr2CaCu2O8+δ at Sub-Unit-Cell Resolution

Xiaowen Zhang, Jiade Li, Xiaoyue Gao +9

The role of phonons in cuprates remains controversial, with their complex lattice structure complicating the investigation. Here, we identify phonon modes originating from charge r…

cs.LG2024

Robust Learning under Hybrid Noise

Yang Wei, Shuo Chen, Shanshan Ye +2

Feature noise and label noise are ubiquitous in practical scenarios, which pose great challenges for training a robust machine learning model. Most previous approaches usually deal…

cs.LG2026

Beyond Distribution Estimation: Simplex Anchored Structural Inference Towards Universal Semi-Supervised Learning

Yaxin Hou, Jun Ma, Hanyang Li +3

Semi-supervised learning faces significant challenges in realistic scenarios where labeled data is scarce and unlabeled data follows unknown, arbitrary distributions. We formalize…

cs.MM2024

AMD: Autoregressive Motion Diffusion

Bo Han, Hao Peng, Minjing Dong +3

Human motion generation aims to produce plausible human motion sequences according to various conditional inputs, such as text or audio. Despite the feasibility of existing methods…

cs.AI2026

MLUBench: A Benchmark for Lifelong Unlearning Evaluation in MLLMs

He Li, Haoang Chi, Qizhou Wang +6

Multimodal large language models (MLLMs) are trained on massive multimodal data, making data unlearning increasingly important as data owners may request the removal of specific co…

cs.CE2026

NFT Games: an Empirical Look into the Play-to-Earn Model

Yixiao Gao, Fei Li, Ruizhe Shi +4

The past decade has witnessed the burgeoning and continuous development of blockchain and its applications. Besides various cryptocurrencies, an industry that has quickly embraced…

cs.CV2025

Keep It on a Leash: Controllable Pseudo-label Generation Towards Realistic Long-Tailed Semi-Supervised Learning

Yaxin Hou, Bo Han, Yuheng Jia +2

Current long-tailed semi-supervised learning methods assume that labeled data exhibit a long-tailed distribution, and unlabeled data adhere to a typical predefined distribution (i.…

cs.CV2024

A Sober Look at the Robustness of CLIPs to Spurious Features

Qizhou Wang, Yong Lin, Yongqiang Chen +3

Large vision language models, such as CLIP, demonstrate impressive robustness to spurious features than single-modal models trained on ImageNet. However, existing test datasets are…

cs.LG2026

Towards Efficient Large Vision-Language Models: A Comprehensive Survey on Inference Strategies

Surendra Pathak, Bo Han

Although Large Vision Language Models (LVLMs) have demonstrated impressive multimodal reasoning capabilities, their scalability and deployment are constrained by massive computatio…

cs.LG2022

Virtual Homogeneity Learning: Defending against Data Heterogeneity in Federated Learning

Zhenheng Tang, Yonggang Zhang, Shaohuai Shi +3

In federated learning (FL), model performance typically suffers from client drift induced by data heterogeneity, and mainstream works focus on correcting client drift. We propose a…

cs.CV2026

PRISM: Streaming Human Motion Generation with Per-Joint Latent Decomposition

Zeyu Ling, Qing Shuai, Teng Zhang +3

Text-to-motion generation has advanced rapidly, yet two challenges persist. First, existing motion autoencoders compress each frame into a single monolithic latent vector, entangli…

cs.LG2022

Reliable Adversarial Distillation with Unreliable Teachers

Jianing Zhu, Jiangchao Yao, Bo Han +6

In ordinary distillation, student networks are trained with soft labels (SLs) given by pretrained teacher networks, and students are expected to improve upon teachers since SLs are…

cs.LG2022

Do We Need to Penalize Variance of Losses for Learning with Label Noise?

Yexiong Lin, Yu Yao, Yuxuan Du +4

Algorithms which minimize the averaged loss have been widely designed for dealing with noisy labels. Intuitively, when there is a finite training sample, penalizing the variance of…

cs.NI2024

A First Look at Immersive Telepresence on Apple Vision Pro

Ruizhi Cheng, Nan Wu, Matteo Varvello +3

Due to the widespread adoption of "work-from-home" policies, videoconferencing applications (e.g., Zoom) have become indispensable for remote communication. However, they often lac…

cs.CR2023

Towards Zero-trust Security for the Metaverse

Ruizhi Cheng, Songqing Chen, Bo Han

By focusing on immersive interaction among users, the burgeoning Metaverse can be viewed as a natural extension of existing social media. Similar to traditional online social netwo…

cs.LG2021

Understanding and Improving Early Stopping for Learning with Noisy Labels

Yingbin Bai, Erkun Yang, Bo Han +5

The memorization effect of deep neural network (DNN) plays a pivotal role in many state-of-the-art label-noise learning methods. To exploit this property, the early stopping trick,…

cs.LG2026

DICE: Entropy-Regularized Equilibrium Selection for Stable Multi-Agent LLM Coordination

Yi Xie, Zhanke Zhou, Chentao Cao +2

Multi-agent large language model (LLM) systems often fail to reliably outperform a single strong model equipped with best-of-N sampling. We argue that a core source of this instabi…

cs.CV2026

Rethinking Model Selection in VLM Through the Lens of Gromov-Wasserstein Distance

Muyang Li, Yucheng Liu, Jianbo Ma +3

Vision-Language Models (VLMs) have enhanced traditional LLMs with visual capabilities through the integration of vision encoders. While recent works have explored various combinati…

cs.CV2022

Pluralistic Image Completion with Probabilistic Mixture-of-Experts

Xiaobo Xia, Wenhao Yang, Jie Ren +4

Pluralistic image completion focuses on generating both visually realistic and diverse results for image completion. Prior methods enjoy the empirical successes of this task. Howev…

cs.LG2021

Sample Selection with Uncertainty of Losses for Learning with Noisy Labels

Xiaobo Xia, Tongliang Liu, Bo Han +4

In learning with noisy labels, the sample selection approach is very popular, which regards small-loss data as correctly labeled during training. However, losses are generated on-t…

cs.CL2024

Physics Reasoner: Knowledge-Augmented Reasoning for Solving Physics Problems with Large Language Models

Xinyu Pang, Ruixin Hong, Zhanke Zhou +5

Physics problems constitute a significant aspect of reasoning, necessitating complicated reasoning ability and abundant physics knowledge. However, existing large language models (…

cs.AI2025

Lang-PINN: From Language to Physics-Informed Neural Networks via a Multi-Agent Framework

Xin He, Liangliang You, Hongduan Tian +3

Physics-informed neural networks (PINNs) provide a powerful approach for solving partial differential equations (PDEs), but constructing a usable PINN remains labor-intensive and e…

cs.LG2021

Geometry-aware Instance-reweighted Adversarial Training

Jingfeng Zhang, Jianing Zhu, Gang Niu +3

In adversarial machine learning, there was a common belief that robustness and accuracy hurt each other. The belief was challenged by recent studies where we can maintain the robus…

cs.LG2023

Federated Semi-Supervised Learning with Annotation Heterogeneity

Xinyi Shang, Gang Huang, Yang Lu +4

Federated Semi-Supervised Learning (FSSL) aims to learn a global model from different clients in an environment with both labeled and unlabeled data. Most of the existing FSSL work…

cs.LG2022

Bilateral Dependency Optimization: Defending Against Model-inversion Attacks

Xiong Peng, Feng Liu, Jingfen Zhang +4

Through using only a well-trained classifier, model-inversion (MI) attacks can recover the data used for training the classifier, leading to the privacy leakage of the training dat…

cs.LG2026

Heterogeneity-Aware Knowledge Sharing for Graph Federated Learning

Wentao Yu, Sheng Wan, Shuo Chen +2

Graph Federated Learning (GFL) enables distributed graph representation learning while protecting the privacy of graph data. However, GFL suffers from heterogeneity arising from di…

cs.LG2023

Exploring Model Dynamics for Accumulative Poisoning Discovery

Jianing Zhu, Xiawei Guo, Jiangchao Yao +6

Adversarial poisoning attacks pose huge threats to various machine learning applications. Especially, the recent accumulative poisoning attacks show that it is possible to achieve…

cs.CV2023

SketchFFusion: Sketch-guided image editing with diffusion model

Weihang Mao, Bo Han, Zihao Wang

Sketch-guided image editing aims to achieve local fine-tuning of the image based on the sketch information provided by the user, while maintaining the original status of the unedit…

cs.LG2020

Searching to Exploit Memorization Effect in Learning from Corrupted Labels

Quanming Yao, Hansi Yang, Bo Han +2

Sample selection approaches are popular in robust learning from noisy labels. However, how to properly control the selection process so that deep networks can benefit from the memo…

cs.AI2026

BoxMind: Closed-loop AI strategy optimization for elite boxing validated in the 2024 Olympics

Kaiwen Wang, Kaili Zheng, Rongrong Deng +8

Competitive sports require sophisticated tactical analysis, yet combat disciplines like boxing remain underdeveloped in AI-driven analytics due to the complexity of action dynamics…

cs.LG2022

Modeling Adversarial Noise for Adversarial Training

Dawei Zhou, Nannan Wang, Bo Han +1

Deep neural networks have been demonstrated to be vulnerable to adversarial noise, promoting the development of defense against adversarial attacks. Motivated by the fact that adve…

cs.CR2018

Privacy-preserving Stochastic Gradual Learning

Bo Han, Ivor W. Tsang, Xiaokui Xiao +3

It is challenging for stochastic optimizations to handle large-scale sensitive data safely. Recently, Duchi et al. proposed private sampling strategy to solve privacy leakage in st…

cond-mat.mtrl-sci2026

Anisotropic nanoscale coherent polariton transport in CrSBr

Paritosh Malik, Dogyun Ko, Vita Solovyeva +11

In a combined experimental and theoretical study, we demonstrate anisotropic polariton transport on the nanoscale in the van der Waals antiferromagnet CrSBr. While effective cavity…

quant-ph2024

Robust teleportation of a surface code and cascade of topological quantum phase transitions

Finn Eckstein, Bo Han, Simon Trebst +1

Teleportation is a facet where quantum measurements can act as a powerful resource in quantum physics, as local measurements allow to steer quantum information in a non-local way.…

cs.LG2023

Detecting Adversarial Data by Probing Multiple Perturbations Using Expected Perturbation Score

Shuhai Zhang, Feng Liu, Jiahao Yang +4

Adversarial detection aims to determine whether a given sample is an adversarial one based on the discrepancy between natural and adversarial distributions. Unfortunately, estimati…

cs.LG2025

Generative Model Inversion Through the Lens of the Manifold Hypothesis

Xiong Peng, Bo Han, Fengfei Yu +3

Model inversion attacks (MIAs) aim to reconstruct class-representative samples from trained models. Recent generative MIAs utilize generative adversarial networks to learn image pr…

math.NA2024

Stochastic gradient descent method with convex penalty for ill-posed problems in Banach spaces

Ruixue Gu, Zhenwu Fu, Bo Han +1

In this work, we investigate a stochastic gradient descent method for solving inverse problems that can be written as systems of linear or nonlinear ill-posed equations in Banach s…

cond-mat.mes-hall2021

Valley-exchange coupling probed by angle-resolved photoluminescence

Joshua J. P Thompson, Samuel Brem, Hanlin Fang +7

The optical properties of monolayer transition metal dichalcogenides are dominated by tightly-bound excitons. They form at distinct valleys in reciprocal space, and can interact vi…

cs.NE2026

What Do Evolutionary Coding Agents Evolve?

Nico Pelleriti, Sree Harsha Nelaturu, Zhanke Zhou +4

Recent work pairs LLMs with evolutionary search to iteratively generate, modify, and select code using task-specific feedback. These systems have produced strong results in mathema…

cond-mat.str-el2017

Boundary conformal field theory and symmetry protected topological phases in dimensions

Bo Han, Apoorv Tiwari, Chang-Tse Hsieh +1

We propose a diagnostic tool for detecting non-trivial symmetry protected topological (SPT) phases protected by a symmetry group in 2+1 dimensions. Our method is based on direc…

cond-mat.mes-hall2026

High-Performance Nanophononic Resonators in Self-Suspended WSe Domes and Drums

Jens-Christian Drawer, Bo Han, Edson Rafael Cardozo de Oliveira +7

Van der Waals materials are ideally suited for the implementation of high-frequency nanophononic resonators with atomically flat interfaces. Here, we present two versatile van der…

cs.CL2026

Multi-Level Contextual Token Relation Modeling for Machine-Generated Text Detection

Chenwang Wu, Yiuming Cheung, Bo Han +2

Machine-generated texts (MGTs) pose risks such as disinformation and phishing, underscoring the need for reliable detection. Metric-based methods, which extract statistically disti…

cs.MM2024

Dance2MIDI: Dance-driven multi-instruments music generation

Bo Han, Yuheng Li, Yixuan Shen +2

Dance-driven music generation aims to generate musical pieces conditioned on dance videos. Previous works focus on monophonic or raw audio generation, while the multi-instruments s…

cs.LG2024

Mitigating Label Noise on Graph via Topological Sample Selection

Yuhao Wu, Jiangchao Yao, Xiaobo Xia +4

Despite the success of the carefully-annotated benchmarks, the effectiveness of existing graph neural networks (GNNs) can be considerably impaired in practice when the real-world g…

cs.LG2023

Harnessing Out-Of-Distribution Examples via Augmenting Content and Style

Zhuo Huang, Xiaobo Xia, Li Shen +4

Machine learning models are vulnerable to Out-Of-Distribution (OOD) examples, and such a problem has drawn much attention. However, current methods lack a full understanding of dif…

cs.LG2022

Robust Weight Perturbation for Adversarial Training

Chaojian Yu, Bo Han, Mingming Gong +4

Overfitting widely exists in adversarial robust training of deep networks. An effective remedy is adversarial weight perturbation, which injects the worst-case weight perturbation…

cs.LG2022

Low-rank Tensor Learning with Nonconvex Overlapped Nuclear Norm Regularization

Quanming Yao, Yaqing Wang, Bo Han +1

Nonconvex regularization has been popularly used in low-rank matrix learning. However, extending it for low-rank tensor learning is still computationally expensive. To address this…

cs.LG2021

Local Reweighting for Adversarial Training

Ruize Gao, Feng Liu, Kaiwen Zhou +3

Instances-reweighted adversarial training (IRAT) can significantly boost the robustness of trained models, where data being less/more vulnerable to the given attack are assigned sm…

cs.LG2024

What If the Input is Expanded in OOD Detection?

Boxuan Zhang, Jianing Zhu, Zengmao Wang +3

Out-of-distribution (OOD) detection aims to identify OOD inputs from unknown classes, which is important for the reliable deployment of machine learning models in the open world. V…

cs.LG2023

Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sources

Haotian Zheng, Qizhou Wang, Zhen Fang +4

Out-of-distribution (OOD) detection discerns OOD data where the predictor cannot make valid predictions as in-distribution (ID) data, thereby increasing the reliability of open-wor…

cs.LG2018

Masking: A New Perspective of Noisy Supervision

Bo Han, Jiangchao Yao, Gang Niu +4

It is important to learn various types of classifiers given training data with noisy labels. Noisy labels, in the most popular noise model hitherto, are corrupted from ground-truth…