4 papers
Multimodal Safety Evaluation in Generative Agent Social Simulations
Alhim Vera, Karen Sanchez, Carlos Hinojosa +3
Can generative agents be trusted in multimodal environments? Despite advances in large language and vision-language models that enable agents to act autonomously and pursue goals i…
Post-Training Quantization via Residual Truncation and Zero Suppression for Diffusion Models
Donghoon Kim, Dongyoung Lee, Ik Joon Chang +1
Diffusion models achieve high-quality image generation but face deployment challenges due to their high computational requirements. Although 8-bit outlier-aware post-training quant…
Offline Policy Learning via Skill-step Abstraction for Long-horizon Goal-Conditioned Tasks
Donghoon Kim, Minjong Yoo, Honguk Woo
Goal-conditioned (GC) policy learning often faces a challenge arising from the sparsity of rewards, when confronting long-horizon goals. To address the challenge, we explore skill-…
Robustness of SAM: Segment Anything Under Corruptions and Beyond
Yu Qiao, Chaoning Zhang, Taegoo Kang +3
Segment anything model (SAM), as the name suggests, is claimed to be capable of cutting out any object and demonstrates impressive zero-shot transfer performance with the guidance…