8 papers
@skills: Attention is all you have
Li Yin, Zhi Li, Zhan Shi +4
There are 56,804 public agent skills today, and teams write many more privately. The dominant delivery model is installation: once installed, a skill's description remains in the s…
CostNav: A Navigation Benchmark for Real-World Economic-Cost Evaluation of Physical AI Agents
Haebin Seong, Sungmin Kim, Yongjun Cho +20
Current navigation benchmarks focus on task success but do not capture the economic constraints essential for commercializing autonomous delivery systems. We introduce CostNav, an…
The Last Harness You'll Ever Build
Haebin Seong, Li Yin, Haoran Zhang +1
AI agents are increasingly deployed on complex, domain-specific workflows -- navigating enterprise web applications that require dozens of clicks and form fills, orchestrating mult…
D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI
Suhwan Choi, Jaeyoon Jung, Haebin Seong +7
Large language models leverage internet-scale text data, yet embodied AI remains constrained by the prohibitive costs of physical trajectory collection. Desktop environments -- par…
BiasJailbreak:Analyzing Ethical Biases and Jailbreak Vulnerabilities in Large Language Models
Isack Lee, Haebin Seong
Although large language models (LLMs) demonstrate impressive proficiency in various tasks, they present potential safety risks, such as `jailbreaks', where malicious inputs can coe…
FedSVD: Adaptive Orthogonalization for Private Federated Learning with LoRA
Seanie Lee, Sangwoo Park, Dong Bok Lee +5
Low-Rank Adaptation (LoRA), which introduces a product of two trainable low-rank matrices into frozen pre-trained weights, is widely used for efficient fine-tuning of language mode…