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…
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…
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…