Zobrazeno 1 - 10
of 2 831
pro vyhledávání: '"Wang,Yuhui"'
The Space-Air-Ground Integrated Network (SAGIN) framework is a crucial foundation for future networks, where satellites and aerial nodes assist in computational task offloading. The low-altitude economy, leveraging the flexibility and multifunctional
Externí odkaz:
http://arxiv.org/abs/2412.10700
Jailbreak attacks circumvent LLMs' built-in safeguards by concealing harmful queries within jailbreak prompts. While existing defenses primarily focus on mitigating the effects of jailbreak prompts, they often prove inadequate as jailbreak prompts ca
Externí odkaz:
http://arxiv.org/abs/2410.19937
Autor:
Wang, Yuhui, Wu, Qingyuan, Li, Weida, Ashley, Dylan R., Faccio, Francesco, Huang, Chao, Schmidhuber, Jürgen
The Value Iteration Network (VIN) is an end-to-end differentiable architecture that performs value iteration on a latent MDP for planning in reinforcement learning (RL). However, VINs struggle to scale to long-term and large-scale planning tasks, suc
Externí odkaz:
http://arxiv.org/abs/2406.08404
Value iteration networks (VINs) enable end-to-end learning for planning tasks by employing a differentiable "planning module" that approximates the value iteration algorithm. However, long-term planning remains a challenge because training very deep
Externí odkaz:
http://arxiv.org/abs/2406.03485
Autor:
Wang, Yuhui, Strupl, Miroslav, Faccio, Francesco, Wu, Qingyuan, Liu, Haozhe, Grudzień, Michał, Tan, Xiaoyang, Schmidhuber, Jürgen
Learning from multi-step off-policy data collected by a set of policies is a core problem of reinforcement learning (RL). Approaches based on importance sampling (IS) often suffer from large variances due to products of IS ratios. Typical IS-free met
Externí odkaz:
http://arxiv.org/abs/2405.18289
Autor:
Wu, Qingyuan, Zhan, Simon Sinong, Wang, Yixuan, Wang, Yuhui, Lin, Chung-Wei, Lv, Chen, Zhu, Qi, Huang, Chao
In environments with delayed observation, state augmentation by including actions within the delay window is adopted to retrieve Markovian property to enable reinforcement learning (RL). However, state-of-the-art (SOTA) RL techniques with Temporal-Di
Externí odkaz:
http://arxiv.org/abs/2405.14226
Topological flat bands (TFBs) are increasingly recognized as an important paradigm to study topological effects in the context of strong correlation physics. As a representative example, recently it has been theoretically proposed that the topologica
Externí odkaz:
http://arxiv.org/abs/2402.09665
Autor:
Wu, Qingyuan, Zhan, Simon Sinong, Wang, Yixuan, Wang, Yuhui, Lin, Chung-Wei, Lv, Chen, Zhu, Qi, Schmidhuber, Jürgen, Huang, Chao
Reinforcement learning (RL) is challenging in the common case of delays between events and their sensory perceptions. State-of-the-art (SOTA) state augmentation techniques either suffer from state space explosion or performance degeneration in stocha
Externí odkaz:
http://arxiv.org/abs/2402.03141
Autor:
Wang, Yuhui, Farooq, Junaid
The advent of fifth generation (5G) networks has opened new avenues for enhancing connectivity, particularly in challenging environments like remote areas or disaster-struck regions. Unmanned aerial vehicles (UAVs) have been identified as a versatile
Externí odkaz:
http://arxiv.org/abs/2312.14247
Autor:
Ji, Zhurun, Zhao, Yuzhou, Chen, Yicong, Zhu, Ziyan, Wang, Yuhui, Liu, Wenjing, Modi, Gaurav, Mele, Eugene J., Jin, Song, Agarwal, Ritesh
Studies of moire systems have elucidated the exquisite effect of quantum geometry on the electronic bands and their properties, leading to the discovery of new correlated phases. However, most experimental studies have been confined to a few layers i
Externí odkaz:
http://arxiv.org/abs/2312.10954