Zobrazeno 1 - 10
of 2 203
pro vyhledávání: '"Singh Aditya"'
Large language models (LLMs) are often equipped with multi-sample decoding strategies. An LLM implicitly defines an arithmetic code book, facilitating efficient and embarrassingly parallelizable \textbf{arithmetic sampling} to produce multiple sample
Externí odkaz:
http://arxiv.org/abs/2411.06251
Autor:
Singh, Aditya Vikram, Rathbun, Ethan, Graham, Emma, Oakley, Lisa, Boboila, Simona, Oprea, Alina, Chin, Peter
Recent advances in multi-agent reinforcement learning (MARL) have created opportunities to solve complex real-world tasks. Cybersecurity is a notable application area, where defending networks against sophisticated adversaries remains a challenging t
Externí odkaz:
http://arxiv.org/abs/2410.17351
Autor:
Singh, Aditya, Wang, Haohan
As per recent studies, Self-supervised learning (SSL) does not readily extend to smaller architectures. One direction to mitigate this shortcoming while simultaneously training a smaller network without labels is to adopt unsupervised knowledge disti
Externí odkaz:
http://arxiv.org/abs/2409.13939
In modern robotics, addressing the lack of accurate state space information in real-world scenarios has led to a significant focus on utilizing visuomotor observation to provide safety assurances. Although supervised learning methods, such as imitati
Externí odkaz:
http://arxiv.org/abs/2409.12616
We introduce multimodal story summarization by leveraging TV episode recaps - short video sequences interweaving key story moments from previous episodes to bring viewers up to speed. We propose PlotSnap, a dataset featuring two crime thriller TV sho
Externí odkaz:
http://arxiv.org/abs/2405.11487
Indian folk paintings have a rich mosaic of symbols, colors, textures, and stories making them an invaluable repository of cultural legacy. The paper presents a novel approach to classifying these paintings into distinct art forms and tagging them wi
Externí odkaz:
http://arxiv.org/abs/2405.08776
Autor:
Singh, Aditya, Reddy, Pavan
Anomaly detection, a critical facet in data analysis, involves identifying patterns that deviate from expected behavior. This research addresses the complexities inherent in anomaly detection, exploring challenges and adapting to sophisticated malici
Externí odkaz:
http://arxiv.org/abs/2405.03075
Hamilton-Jacobi (HJ) reachability analysis is a widely adopted verification tool to provide safety and performance guarantees for autonomous systems. However, it involves solving a partial differential equation (PDE) to compute a safety value functio
Externí odkaz:
http://arxiv.org/abs/2404.00814
Enhancing the robustness of deep learning models, particularly in the realm of vision transformers (ViTs), is crucial for their real-world deployment. In this work, we provide a finetuning approach to enhance the robustness of vision transformers ins
Externí odkaz:
http://arxiv.org/abs/2403.10476
Autor:
Goel, Drishti, Husain, Fiza, Singh, Aditya, Ghosh, Supriyo, Parayil, Anjaly, Bansal, Chetan, Zhang, Xuchao, Rajmohan, Saravan
Incident management for large cloud services is a complex and tedious process and requires significant amount of manual efforts from on-call engineers (OCEs). OCEs typically leverage data from different stages of the software development lifecycle [S
Externí odkaz:
http://arxiv.org/abs/2404.03662