1 citations · 3 across the 13 of their papers we have counts for
13 papers
Compression as an Adversarial Amplifier Through Decision Space Reduction
Lewis Evans, Harkrishan Jandu, Zihan Ye +2
Image compression is a ubiquitous component of modern visual pipelines, routinely applied by social media platforms and resource-constrained systems prior to inference. Despite its…
Low-Effort Jailbreak Attacks Against Text-to-Image Safety Filters
Ahmed B Mustafa, Zihan Ye, Yang Lu +2
Text-to-image generative models are widely deployed in creative tools and online platforms. To mitigate misuse, these systems rely on safety filters and moderation pipelines that a…
Boosting deep Reinforcement Learning using pretraining with Logical Options
Zihan Ye, Phil Chau, Raban Emunds +5
Deep reinforcement learning agents are often misaligned, as they over-exploit early reward signals. Recently, several symbolic approaches have addressed these challenges by encodin…
ZeroDiff++: Substantial Unseen Visual-semantic Correlation in Zero-shot Learning
Zihan Ye, Shreyank N Gowda, Kaile Du +2
Zero-shot Learning (ZSL) enables classifiers to recognize classes unseen during training, commonly via generative two stage methods: (1) learn visual semantic correlations from see…
SWE-AGI: Benchmarking Specification-Driven Software Construction with MoonBit in the Era of Autonomous Agents
Zhirui Zhang, Hongbo Zhang, Haoxiang Fei +11
Although large language models (LLMs) have demonstrated impressive coding capabilities, their ability to autonomously build production-scale software from explicit specifications r…
Adversarial Robustness in Zero-Shot Learning:An Empirical Study on Class and Concept-Level Vulnerabilities
Zhiyuan Peng, Zihan Ye, Shreyank N Gowda +3
Zero-shot Learning (ZSL) aims to enable image classifiers to recognize images from unseen classes that were not included during training. Unlike traditional supervised classificati…
DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP
Kaile Du, Zihan Ye, Junzhou Xie +7
Multi-label class-incremental learning (MLCIL) continuously expands the label space while recognizing multiple co-occurring categories, making catastrophic forgetting a central cha…
Anyone Can Jailbreak: Prompt-Based Attacks on LLMs and T2Is
Ahmed B Mustafa, Zihan Ye, Yang Lu +2
Despite significant advancements in alignment and content moderation, large language models (LLMs) and text-to-image (T2I) systems remain vulnerable to prompt-based attacks known a…
Learning from Less: Guiding Deep Reinforcement Learning with Differentiable Symbolic Planning
Zihan Ye, Oleg Arenz, Kristian Kersting
When tackling complex problems, humans naturally break them down into smaller, manageable subtasks and adjust their initial plans based on observations. For instance, if you want t…
Interpretable Zero-shot Learning with Infinite Class Concepts
Zihan Ye, Shreyank N Gowda, Shiming Chen +3
Zero-shot learning (ZSL) aims to recognize unseen classes by aligning images with intermediate class semantics, like human-annotated concepts or class definitions. An emerging alte…
Think Small, Plan Smart: Minimalist Symbolic Abstraction and Heuristic Subspace Search for LLM-Guided Task Planning
Junfeng Tang, Yuping Yan, Zihan Ye +4
Reliable task planning is pivotal for achieving long-horizon autonomy in real-world robotic systems. Large language models (LLMs) offer a promising interface for translating comple…
Improved Feature Generating Framework for Transductive Zero-shot Learning
Zihan Ye, Xinyuan Ru, Shiming Chen +3
Feature Generative Adversarial Networks have emerged as powerful generative models in producing high-quality representations of unseen classes within the scope of Zero-shot Learnin…
ZeroDiff: Solidified Visual-Semantic Correlation in Zero-Shot Learning
Zihan Ye, Shreyank N. Gowda, Xiaowei Huang +4
Zero-shot Learning (ZSL) aims to enable classifiers to identify unseen classes. This is typically achieved by generating visual features for unseen classes based on learned visual-…