8 papers
LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering
Yi Wang, Haopeng Zhang, Chengxiang Huang +4
Loop Engineering is emerging as a practice for organizing development work around coding agents. Instead of writing each prompt by hand, practitioners design loops that monitor pro…
Possibilistic Predictive Uncertainty for Deep Learning
Yao Ni, Jeremie Houssineau, Yew-Soon Ong +1
Deep neural networks achieve impressive results across diverse applications, yet their overconfidence on unseen inputs necessitates reliable epistemic uncertainty modeling. Existin…
Beyond Attack Success Rate: Examining Trigger Leakage in Vision-Language Agentic Systems
Jiamin Chang, Salil Kanhere, Piotr Koniusz +3
Vision-Language Agentic Systems (VLAS) connect visual perception to planning, tool use, and physical actions. This means backdoor-type triggers can propagate through both decision…
ICED: Concept-level Machine Unlearning via Interpretable Concept Decomposition
Shen Lin, Jing Lin, Junhao Dong +2
Machine unlearning in Vision-Language Models (VLMs) is typically performed at the image or instance level, making it difficult to precisely remove target knowledge without affectin…
DeCo-DETR: Decoupled Cognition DETR for efficient Open-Vocabulary Object Detection
Siheng Wang, Yanshu Li, Bohan Hu +12
Open-vocabulary object detection (OVOD) enables models to recognize objects beyond predefined categories, but existing approaches remain limited in practical deployment. On the one…
Hierarchically Robust Zero-shot Vision-language Models
Junhao Dong, Yifei Zhang, Hao Zhu +2
Vision-Language Models (VLMs) can perform zero-shot classification but are susceptible to adversarial attacks. While robust fine-tuning improves their robustness, existing approach…
MMT-ARD: Multimodal Multi-Teacher Adversarial Distillation for Robust Vision-Language Models
Yuqi Li, Junhao Dong, Chuanguang Yang +5
Vision-Language Models (VLMs) are increasingly deployed in safety-critical applications, making their adversarial robustness a crucial concern. While adversarial knowledge distilla…
C3-OWD: A Curriculum Cross-modal Contrastive Learning Framework for Open-World Detection
Siheng Wang, Zhengdao Li, Yanshu Li +12
Object detection has advanced significantly in the closed-set setting, but real-world deployment remains limited by two challenges: poor generalization to unseen categories and ins…