Výsledky vyhledávání - "Duan, Haonan"

Report

Can LLMs Understand Social Norms in Autonomous Driving Games?

Autor: Wang, Boxuan, Duan, Haonan, Feng, Yanhao, Chen, Xu, Fu, Yongjie, Mo, Zhaobin, Di, Xuan

Social norm is defined as a shared standard of acceptable behavior in a society. The emergence of social norms fosters coordination among agents without any hard-coded rules, which is crucial for the large-scale deployment of AVs in an intelligent tr

Externí odkaz: http://arxiv.org/abs/2408.12680

Zobrazit plný text záznamu

Report

Meta-Designing Quantum Experiments with Language Models

Autor: Arlt, Sören, Duan, Haonan, Li, Felix, Xie, Sang Michael, Wu, Yuhuai, Krenn, Mario

Artificial Intelligence (AI) has the potential to significantly advance scientific discovery by finding solutions beyond human capabilities. However, these super-human solutions are often unintuitive and require considerable effort to uncover underly

Externí odkaz: http://arxiv.org/abs/2406.02470

Zobrazit plný text záznamu

Report

Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models

Autor: Duan, Haonan, Dziedzic, Adam, Papernot, Nicolas, Boenisch, Franziska

Large language models (LLMs) are excellent in-context learners. However, the sensitivity of data contained in prompts raises privacy concerns. Our work first shows that these concerns are valid: we instantiate a simple but highly effective membership

Externí odkaz: http://arxiv.org/abs/2305.15594

Zobrazit plný text záznamu

Report

Progressive Transfer Learning for Dexterous In-Hand Manipulation with Multi-Fingered Anthropomorphic Hand

Autor: Luo, Yongkang, Li, Wanyi, Wang, Peng, Duan, Haonan, Wei, Wei, Sun, Jia

Dexterous in-hand manipulation for a multi-fingered anthropomorphic hand is extremely difficult because of the high-dimensional state and action spaces, rich contact patterns between the fingers and objects. Even though deep reinforcement learning ha

Externí odkaz: http://arxiv.org/abs/2304.09526

Zobrazit plný text záznamu

Report

Dataset Inference for Self-Supervised Models

Autor: Dziedzic, Adam, Duan, Haonan, Kaleem, Muhammad Ahmad, Dhawan, Nikita, Guan, Jonas, Cattan, Yannis, Boenisch, Franziska, Papernot, Nicolas

Self-supervised models are increasingly prevalent in machine learning (ML) since they reduce the need for expensively labeled data. Because of their versatility in downstream applications, they are increasingly used as a service exposed via public AP

Externí odkaz: http://arxiv.org/abs/2209.09024

Zobrazit plný text záznamu

Report

Augment with Care: Contrastive Learning for Combinatorial Problems

Autor: Duan, Haonan, Vaezipoor, Pashootan, Paulus, Max B., Ruan, Yangjun, Maddison, Chris J.

Supervised learning can improve the design of state-of-the-art solvers for combinatorial problems, but labelling large numbers of combinatorial instances is often impractical due to exponential worst-case complexity. Inspired by the recent success of

Externí odkaz: http://arxiv.org/abs/2202.08396

Zobrazit plný text záznamu