Publications (96)
Beam energy dependence of and productions in Au+Au collisions at RHIC
Ning Yu
Light nuclei have much smaller binding energy compared to the temperature of the system created in heavy-ion collisions. Consequently, the distributions of light nuclei can be used…
Vista4D: Video Reshooting with 4D Point Clouds
Kuan Heng Lin, Zhizheng Liu, Pablo Salamanca +9
We present Vista4D, a robust and flexible video reshooting framework that grounds the input video and target cameras in a 4D point cloud. Specifically, given an input video, our me…
HIVE: Harnessing Human Feedback for Instructional Visual Editing
Shu Zhang, Xinyi Yang, Yihao Feng +9
Incorporating human feedback has been shown to be crucial to align text generated by large language models to human preferences. We hypothesize that state-of-the-art instructional…
AugTriever: Unsupervised Dense Retrieval and Domain Adaptation by Scalable Data Augmentation
Rui Meng, Ye Liu, Semih Yavuz +6
Dense retrievers have made significant strides in text retrieval and open-domain question answering. However, most of these achievements have relied heavily on extensive human-anno…
UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild
Can Qin, Shu Zhang, Ning Yu +10
Achieving machine autonomy and human control often represent divergent objectives in the design of interactive AI systems. Visual generative foundation models such as Stable Diffus…
JIGMARK: A Black-Box Approach for Enhancing Image Watermarks against Diffusion Model Edits
Minzhou Pan, Yi Zeng, Xue Lin +4
In this study, we investigate the vulnerability of image watermarks to diffusion-model-based image editing, a challenge exacerbated by the computational cost of accessing gradient…
Study the structure of X(3872) from its lineshape
Hongge Xu, Ning Yu, Zuman Zhang
We fit the invariant mass distribution of from LHCb using the propagator for S-wave near-threshold states in effective field theory. In this wa…
Exploring Nanoscale Photoresponse Mechanisms for Enhanced Photothermoelectric Effects in van der Waals Interfaces
Da Xu, Qiushi Liu, Boqun Liang +7
Integrated photodetectors are crucial for their high speed, sensitivity, and efficient power consumption. In these devices, photocurrent generation is primarily attributed to the p…
Reconstruction of Hidden Representation for Robust Feature Extraction
Zeng Yu, Tianrui Li, Ning Yu +3
This paper aims to develop a new and robust approach to feature representation. Motivated by the success of Auto-Encoders, we first theoretical summarize the general properties of…
VChain: Chain-of-Visual-Thought for Reasoning in Video Generation
Ziqi Huang, Ning Yu, Gordon Chen +3
Recent video generation models can produce smooth and visually appealing clips, but they often struggle to synthesize complex dynamics with a coherent chain of consequences. Accura…
Membership Inference Attack Against Masked Image Modeling
Zheng Li, Xinlei He, Ning Yu +1
Masked Image Modeling (MIM) has achieved significant success in the realm of self-supervised learning (SSL) for visual recognition. The image encoder pre-trained through MIM, invol…
Hierarchical Point Attention for Indoor 3D Object Detection
Manli Shu, Le Xue, Ning Yu +5
3D object detection is an essential vision technique for various robotic systems, such as augmented reality and domestic robots. Transformers as versatile network architectures hav…
FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution
Gene Chou, Wenqi Xian, Guandao Yang +5
A versatile video depth estimation model should (1) be accurate and consistent across frames, (2) produce high-resolution depth maps, and (3) support real-time streaming. We propos…
Learning to Detect Multiple Photographic Defects
Ning Yu, Xiaohui Shen, Zhe Lin +2
In this paper, we introduce the problem of simultaneously detecting multiple photographic defects. We aim at detecting the existence, severity, and potential locations of common ph…
Neutron density fluctuation and neutron-proton correlation from AMPT model
Zuman Zhang, Ning Yu, Hongge Xu
Using the multiphase transport (AMPT) model, we study the relative neutron density fluctuation and neutron-proton correlation in matter produced by Au+Au collisions at $\sqrt{s_\te…
Inclusive GAN: Improving Data and Minority Coverage in Generative Models
Ning Yu, Ke Li, Peng Zhou +3
Generative Adversarial Networks (GANs) have brought about rapid progress towards generating photorealistic images. Yet the equitable allocation of their modeling capacity among sub…
Long-Tailed Recognition Using Class-Balanced Experts
Saurabh Sharma, Ning Yu, Mario Fritz +1
Deep learning enables impressive performance in image recognition using large-scale artificially-balanced datasets. However, real-world datasets exhibit highly class-imbalanced dis…
Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders
Zeyang Sha, Xinlei He, Ning Yu +2
Self-supervised representation learning techniques have been developing rapidly to make full use of unlabeled images. They encode images into rich features that are oblivious to do…
On the Proactive Generation of Unsafe Images From Text-To-Image Models Using Benign Prompts
Yixin Wu, Ning Yu, Michael Backes +2
Malicious or manipulated prompts are known to exploit text-to-image models to generate unsafe images. Existing studies, however, focus on the passive exploitation of such harmful c…
Inside the Black Box: Detecting Data Leakage in Pre-trained Language Encoders
Yuan Xin, Zheng Li, Ning Yu +4
Despite being prevalent in the general field of Natural Language Processing (NLP), pre-trained language models inherently carry privacy and copyright concerns due to their nature o…
LayoutDETR: Detection Transformer Is a Good Multimodal Layout Designer
Ning Yu, Chia-Chih Chen, Zeyuan Chen +6
Graphic layout designs play an essential role in visual communication. Yet handcrafting layout designs is skill-demanding, time-consuming, and non-scalable to batch production. Gen…
FASTTRACK: Fast and Accurate Fact Tracing for LLMs
Si Chen, Feiyang Kang, Ning Yu +1
Fact tracing seeks to identify specific training examples that serve as the knowledge source for a given query. Existing approaches to fact tracing rely on assessing the similarity…
Go-with-the-Track: Video Compositing and Motion Control with Point Tracking
Koichi Namekata, Yash Kant, Zhizheng Liu +9
Filmmaking demands precise motion control and reference image compositing -- capabilities that existing methods treat separately. Point-track-conditioned image-to-video models rest…
Study of QCD critical point with three-nucleon correlations in light nuclei yields ratios using PYTHIA8/Angantyr
Zuman Zhang, Ning Yu, Sha Li +3
This study utilizes the PYTHIA8 Angantyr model to systematically investigate the effects of three nucleons correlation on the light nuclei yield ratio in…
GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models
Dingfan Chen, Ning Yu, Yang Zhang +1
Deep learning has achieved overwhelming success, spanning from discriminative models to generative models. In particular, deep generative models have facilitated a new level of per…
ReAge3D: Re-Aging 3D Faces with View Consistency
Libing Zeng, Li Ma, Mingming He +3
We present a novel framework for realistic and controllable 3D face re-aging which produces highly detailed, identity-preserving results. Existing 3D editing methods, while effecti…
AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectors
You-Ming Chang, Chen Yeh, Wei-Chen Chiu +1
Deep generative models can create remarkably photorealistic fake images while raising concerns about misinformation and copyright infringement, known as deepfake threats. Deepfake…
Deep Video Inpainting Detection
Peng Zhou, Ning Yu, Zuxuan Wu +3
This paper studies video inpainting detection, which localizes an inpainted region in a video both spatially and temporally. In particular, we introduce VIDNet, Video Inpainting De…
RelaxLoss: Defending Membership Inference Attacks without Losing Utility
Dingfan Chen, Ning Yu, Mario Fritz
As a long-term threat to the privacy of training data, membership inference attacks (MIAs) emerge ubiquitously in machine learning models. Existing works evidence strong connection…
Responsible Disclosure of Generative Models Using Scalable Fingerprinting
Ning Yu, Vladislav Skripniuk, Dingfan Chen +2
Over the past years, deep generative models have achieved a new level of performance. Generated data has become difficult, if not impossible, to be distinguished from real data. Wh…
Detail Enhanced Gaussian Splatting for Large-Scale Volumetric Capture
Julien Philip, Li Ma, Pascal Clausen +8
We present a unique system for large-scale, multi-performer, high resolution 4D volumetric capture providing realistic free-viewpoint video up to and including 4K resolution facial…
Light Nuclei Production in Au+Au Collisions at = 5-200 GeV from JAM model
Hui Liu, Dingwei Zhang, Shu He +3
Light nuclei production is sensitive to the baryon density fluctuations and can be used to probe the QCD phase transition in relativistic heavy-ion collisions. In this work, we stu…
The general propagator for S-wave threshold states
Hongge Xu, Ning Yu, Zuman Zhang +1
We demonstrate that the propagator, derived from an Effective Field Theory (EFT) that incorporates Weinberger's compositeness theorem, provides a more general formula for describin…
MAViS: A Multi-Agent Framework for Long-Sequence Video Storytelling
Qian Wang, Ziqi Huang, Ruoxi Jia +2
Despite recent advances, long-sequence video generation frameworks still suffer from significant limitations: poor assistive capability, suboptimal visual quality, and limited expr…
Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints
Ning Yu, Larry Davis, Mario Fritz
Recent advances in Generative Adversarial Networks (GANs) have shown increasing success in generating photorealistic images. But they also raise challenges to visual forensics and…
Curvature-induced stiffening of a fish fin
Khoi Nguyen, Ning Yu, Mahesh M. Bandi +2
How fish modulate their fin stiffness during locomotive manoeuvres remains unknown. We show that changing the fin's curvature modulates its stiffness. Modelling the fin as bendable…
Keys to Better Image Inpainting: Structure and Texture Go Hand in Hand
Jitesh Jain, Yuqian Zhou, Ning Yu +1
Deep image inpainting has made impressive progress with recent advances in image generation and processing algorithms. We claim that the performance of inpainting algorithms can be…
ID-V2V: Identity-Preserving Video Restylization
Yuancheng Xu, Mingming He, Pablo Salamanca +5
In visual storytelling, human performances are central to creative intent and narrative meaning. However, preserving human identity and performance while enabling flexible visual e…
CineScale: Free Lunch in High-Resolution Cinematic Visual Generation
Haonan Qiu, Ning Yu, Ziqi Huang +2
Visual diffusion models achieve remarkable progress, yet they are typically trained at limited resolutions due to the lack of high-resolution data and constrained computation resou…
KNN, An Underestimated Model for Regional Rainfall Forecasting
Ning Yu, Timothy Haskins
Regional rainfall forecasting is an important issue in hydrology and meteorology. This paper aims to design an integrated tool by applying various machine learning algorithms, espe…
Text2Data: Low-Resource Data Generation with Textual Control
Shiyu Wang, Yihao Feng, Tian Lan +6
Natural language serves as a common and straightforward signal for humans to interact seamlessly with machines. Recognizing the importance of this interface, the machine learning c…
AI-Powered GUI Attack and Its Defensive Methods
Ning Yu, Zachary Tuttle, Carl Jake Thurnau +1
Since the first Graphical User Interface (GUI) prototype was invented in the 1970s, GUI systems have been deployed into various personal computer systems and server platforms. Rece…
Texture Mixer: A Network for Controllable Synthesis and Interpolation of Texture
Ning Yu, Connelly Barnes, Eli Shechtman +2
This paper addresses the problem of interpolating visual textures. We formulate this problem by requiring (1) by-example controllability and (2) realistic and smooth interpolation…
VidLeaks: Membership Inference Attacks Against Text-to-Video Models
Li Wang, Wenyu Chen, Ning Yu +2
The proliferation of powerful Text-to-Video (T2V) models, trained on massive web-scale datasets, raises urgent concerns about copyright and privacy violations. Membership inference…
Investigating nonflow contribution subtraction in d-Au collisions with AMPT model
Zuman Zhang, Sha Li, Ning Yu +1
This paper presents research that focuses on nonflow contribution subtraction in heavy-ion collisions, using a multiphase transport model (AMPT). Specifically, the study aims to in…
ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding
Le Xue, Ning Yu, Shu Zhang +8
Recent advancements in multimodal pre-training have shown promising efficacy in 3D representation learning by aligning multimodal features across 3D shapes, their 2D counterparts,…
Auditing Membership Leakages of Multi-Exit Networks
Zheng Li, Yiyong Liu, Xinlei He +3
Relying on the fact that not all inputs require the same amount of computation to yield a confident prediction, multi-exit networks are gaining attention as a prominent approach fo…
Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models
Yuancheng Xu, Jiarui Yao, Manli Shu +5
Vision-Language Models (VLMs) excel in generating textual responses from visual inputs, but their versatility raises security concerns. This study takes the first step in exposing…
Membership Inference Attacks Against Text-to-image Generation Models
Yixin Wu, Ning Yu, Zheng Li +2
Text-to-image generation models have recently attracted unprecedented attention as they unlatch imaginative applications in all areas of life. However, developing such models requi…
Mask-free OVIS: Open-Vocabulary Instance Segmentation without Manual Mask Annotations
Vibashan VS, Ning Yu, Chen Xing +5
Existing instance segmentation models learn task-specific information using manual mask annotations from base (training) categories. These mask annotations require tremendous human…
RepMix: Representation Mixing for Robust Attribution of Synthesized Images
Tu Bui, Ning Yu, John Collomosse
Rapid advances in Generative Adversarial Networks (GANs) raise new challenges for image attribution; detecting whether an image is synthetic and, if so, determining which GAN archi…
Search for the QCD Critical Point by Transverse Velocity Dependence of Anti-deuteron to Deuteron Ratio
Ning Yu, Dingwei Zhang, Xiaofeng Luo
We propose the transverse velocity () dependence of the anti-deuteron to deuteron ratio as a new observable to search for the QCD critical point in heavy-ion collisions. The…
Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models
Yingkai Dong, Xiangtao Meng, Ning Yu +2
Text-to-image (T2I) generative models have revolutionized content creation by transforming textual descriptions into high-quality images. However, these models are vulnerable to ja…
Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generation
Zeqi Xiao, Yiwei Zhao, Lingxiao Li +6
We investigate whether video generative models can exhibit visuospatial intelligence, a capability central to human cognition, using only visual data. To this end, we present Video…
C-RAG: Certified Generation Risks for Retrieval-Augmented Language Models
Mintong Kang, Nezihe Merve Gürel, Ning Yu +2
Despite the impressive capabilities of large language models (LLMs) across diverse applications, they still suffer from trustworthiness issues, such as hallucinations and misalignm…
RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content
Zhuowen Yuan, Zidi Xiong, Yi Zeng +4
Recent advancements in Large Language Models (LLMs) have showcased remarkable capabilities across various tasks in different domains. However, the emergence of biases and the poten…
DifFRelight: Diffusion-Based Facial Performance Relighting
Mingming He, Pascal Clausen, Ahmet Levent TaÅel +8
We present a novel framework for free-viewpoint facial performance relighting using diffusion-based image-to-image translation. Leveraging a subject-specific dataset containing div…
Detecting Adversarial Faces Using Only Real Face Self-Perturbations
Qian Wang, Yongqin Xian, Hefei Ling +5
Adversarial attacks aim to disturb the functionality of a target system by adding specific noise to the input samples, bringing potential threats to security and robustness when ap…
UnGANable: Defending Against GAN-based Face Manipulation
Zheng Li, Ning Yu, Ahmed Salem +3
Deepfakes pose severe threats of visual misinformation to our society. One representative deepfake application is face manipulation that modifies a victim's facial attributes in an…
Effect of Light Nuclei on Chemical Freeze-out Parameters at RHIC Energies
Ning Yu, Zuman Zhang, Hongge Xu +1
In this study, the chemical freeze-out of hadrons, including light-and strange-flavor particles and light nuclei, produced in Au+Au collisions at the Relativistic Heavy Ion Collide…
Particle decay from statistical thermal model in high energy nucleus-nucleus collision
Ning Yu, Xiaofeng Luo
In high energy nucleus-nucleus collisions, it is difficult to measure the contributions of resonance strong decay and weak decay to the final measured hadrons as well as the corres…
UMDFood: Vision-language models boost food composition compilation
Peihua Ma, Yixin Wu, Ning Yu +4
Nutrition information is crucial in precision nutrition and the food industry. The current food composition compilation paradigm relies on laborious and experience-dependent method…
AI-Educational Development Loop (AI-EDL): A Conceptual Framework to Bridge AI Capabilities with Classical Educational Theories
Ning Yu, Jie Zhang, Sandeep Mitra +2
This study introduces the AI-Educational Development Loop (AI-EDL), a theory-driven framework that integrates classical learning theories with human-in-the-loop artificial intellig…
FreeOrbit4D: Training-Free Arbitrary Camera Redirection for Monocular Videos via Foreground-Complete 4D Reconstruction
Wei Cao, Hao Zhang, Fengrui Tian +5
Camera redirection aims to replay a dynamic scene from a single monocular video under a user-specified camera trajectory. However, large-angle redirection is inherently ill-posed:…
DREAM: Improving Video-Text Retrieval Through Relevance-Based Augmentation Using Large Foundation Models
Yimu Wang, Shuai Yuan, Bo Xue +4
Recent progress in video-text retrieval has been driven largely by advancements in model architectures and training strategies. However, the representation learning capabilities of…
Virtually Being: Customizing Camera-Controllable Video Diffusion Models with Multi-View Performance Captures
Yuancheng Xu, Wenqi Xian, Li Ma +10
We introduce a framework that enables both multi-view character consistency and 3D camera control in video diffusion models through a novel customization data pipeline. We train th…
Generated Graph Detection
Yihan Ma, Zhikun Zhang, Ning Yu +4
Graph generative models become increasingly effective for data distribution approximation and data augmentation. While they have aroused public concerns about their malicious misus…
Three-Stream Convolutional Networks for Video-based Person Re-Identification
Zeng Yu, Tianrui Li, Ning Yu +3
This paper aims to develop a new architecture that can make full use of the feature maps of convolutional networks. To this end, we study a number of methods for video-based person…
Detecting Adversarial Data using Perturbation Forgery
Qian Wang, Chen Li, Yuchen Luo +4
As a defense strategy against adversarial attacks, adversarial detection aims to identify and filter out adversarial data from the data flow based on discrepancies in distribution…
GlueGen: Plug and Play Multi-modal Encoders for X-to-image Generation
Can Qin, Ning Yu, Chen Xing +6
Text-to-image (T2I) models based on diffusion processes have achieved remarkable success in controllable image generation using user-provided captions. However, the tight coupling…
Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis
Yang He, Ning Yu, Margret Keuper +1
The rapid advances in deep generative models over the past years have led to highly {realistic media, known as deepfakes,} that are commonly indistinguishable from real to human ey…
X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning
Artemis Panagopoulou, Le Xue, Ning Yu +7
Recent research has achieved significant advancements in visual reasoning tasks through learning image-to-language projections and leveraging the impressive reasoning abilities of…
Survey of Video Diffusion Models: Foundations, Implementations, and Applications
Yimu Wang, Xuye Liu, Wei Pang +4
Recent advances in diffusion models have revolutionized video generation, offering superior temporal consistency and visual quality compared to traditional generative adversarial n…
Three-Nucleon Correlations in Light Nuclei Yields Ratios from AMPT Model for QCD Critical Point Investigation
Ning Yu, Zuman Zhang, Hongge Xu +1
This research use the AMPT model in Au+Au collisions to study the influence of the three nucleons correlation on the light nuclei yield ratios. It is found that neglecti…
DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Models
Zeyang Sha, Zheng Li, Ning Yu +1
Text-to-image generation models that generate images based on prompt descriptions have attracted an increasing amount of attention during the past few months. Despite their encoura…
AUGUSTUS: An LLM-Driven Multimodal Agent System with Contextualized User Memory
Jitesh Jain, Shubham Maheshwari, Ning Yu +2
Riding on the success of LLMs with retrieval-augmented generation (RAG), there has been a growing interest in augmenting agent systems with external memory databases. However, the…
Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data
Ning Yu, Vladislav Skripniuk, Sahar Abdelnabi +1
Photorealistic image generation has reached a new level of quality due to the breakthroughs of generative adversarial networks (GANs). Yet, the dark side of such deepfakes, the mal…
Reference-Based 3D-Aware Image Editing with Triplanes
Bahri Batuhan Bilecen, Yigit Yalin, Ning Yu +1
Generative Adversarial Networks (GANs) have emerged as powerful tools for high-quality image generation and real image editing by manipulating their latent spaces. Recent advanceme…
T2Vs Meet VLMs: A Scalable Multimodal Dataset for Visual Harmfulness Recognition
Chen Yeh, You-Ming Chang, Wei-Chen Chiu +1
To address the risks of encountering inappropriate or harmful content, researchers managed to incorporate several harmful contents datasets with machine learning methods to detect…
A comparative study of versus production in collisions at 7 TeV
Hongge Xu, Tianqi Luo, Yi-Long Xie +3
The production of exotic hadrons and in collisions at TeV is compared using the parton and hadron cascade model PACIAE together with the dynami…
Dual Contrastive Loss and Attention for GANs
Ning Yu, Guilin Liu, Aysegul Dundar +4
Generative Adversarial Networks (GANs) produce impressive results on unconditional image generation when powered with large-scale image datasets. Yet generated images are still eas…
xGen-MM (BLIP-3): A Family of Open Large Multimodal Models
Le Xue, Manli Shu, Anas Awadalla +30
This paper introduces BLIP-3, an open framework for developing Large Multimodal Models (LMMs). The framework comprises meticulously curated datasets, a training recipe, model archi…
Generated Distributions Are All You Need for Membership Inference Attacks Against Generative Models
Minxing Zhang, Ning Yu, Rui Wen +2
Generative models have demonstrated revolutionary success in various visual creation tasks, but in the meantime, they have been exposed to the threat of leaking private information…
Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise
Ryan Burgert, Yuancheng Xu, Wenqi Xian +10
Generative modeling aims to transform random noise into structured outputs. In this work, we enhance video diffusion models by allowing motion control via structured latent noise s…
Lux Post Facto: Learning Portrait Performance Relighting with Conditional Video Diffusion and a Hybrid Dataset
Yiqun Mei, Mingming He, Li Ma +9
Video portrait relighting remains challenging because the results need to be both photorealistic and temporally stable. This typically requires a strong model design that can captu…
Infinite-Resolution Integral Noise Warping for Diffusion Models
Yitong Deng, Winnie Lin, Lingxiao Li +5
Adapting pretrained image-based diffusion models to generate temporally consistent videos has become an impactful generative modeling research direction. Training-free noise-space…
Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs
Hui-Po Wang, Ning Yu, Mario Fritz
While Generative Adversarial Networks (GANs) show increasing performance and the level of realism is becoming indistinguishable from natural images, this also comes with high deman…
6 nm super-resolution optical transmission and scattering spectroscopic imaging of carbon nanotubes using a nanometer-scale white light source
Xuezhi Ma, Qiushi Liu, Ning Yu +7
Optical hyperspectral imaging based on absorption and scattering of photons at the visible and adjacent frequencies denotes one of the most informative and inclusive characterizati…
RoSteALS: Robust Steganography using Autoencoder Latent Space
Tu Bui, Shruti Agarwal, Ning Yu +1
Data hiding such as steganography and invisible watermarking has important applications in copyright protection, privacy-preserved communication and content provenance. Existing wo…
EMODIS: A Benchmark for Context-Dependent Emoji Disambiguation in Large Language Models
Jiacheng Huang, Ning Yu, Xiaoyin Yi
Large language models (LLMs) are increasingly deployed in real-world communication settings, yet their ability to resolve context-dependent ambiguity remains underexplored. In this…
Continual Adversarial Defense
Qian Wang, Hefei Ling, Yingwei Li +3
In response to the rapidly evolving nature of adversarial attacks against visual classifiers, numerous defenses have been proposed to generalize against as many known attacks as po…
Beyond the Safety Tax: Mitigating Unsafe Text-to-Image Generation via External Safety Rectification
Xiangtao Meng, Yingkai Dong, Ning Yu +3
Text-to-image (T2I) generative models have achieved remarkable visual fidelity, yet remain vulnerable to generating unsafe content. Existing safety defenses typically intervene int…
Learning Prototype Classifiers for Long-Tailed Recognition
Saurabh Sharma, Yongqin Xian, Ning Yu +1
The problem of long-tailed recognition (LTR) has received attention in recent years due to the fundamental power-law distribution of objects in the real-world. Most recent works in…
DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models
Zhengming Yu, Li Ma, Mingming He +11
Most digital videos are stored in 8-bit low dynamic range (LDR) formats, where much of the original high dynamic range (HDR) scene radiance is lost due to saturation and quantizati…
Switchable selective interactions in a Dicke Model with Driven Biased term
Ning Yu, Shiran Wang, Chunfang Sun +1
In this work, we propose a method to investigate controllable qubit-resonator interactions in a Dicke model with driven biased term. The nonlinearity of spectrum, which can be indu…
SimSCOOD: Systematic Analysis of Out-of-Distribution Generalization in Fine-tuned Source Code Models
Hossein Hajipour, Ning Yu, Cristian-Alexandru Staicu +1
Large code datasets have become increasingly accessible for pre-training source code models. However, for the fine-tuning phase, obtaining representative training data that fully c…