Zobrazeno 1 - 10
of 467
pro vyhledávání: '"Varshney, Lav R."'
Autor:
Pattanaik, Anay, Varshney, Lav R.
This paper considers an online reinforcement learning algorithm that leverages pre-collected data (passive memory) from the environment for online interaction. We show that using passive memory improves performance and further provide theoretical gua
Externí odkaz:
http://arxiv.org/abs/2410.14665
Autor:
Nayak, Anuj K., Varshney, Lav R.
Recent empirical studies show three phenomena with increasing size of language models: compute-optimal size scaling, emergent capabilities, and performance plateauing. We present a simple unified mathematical framework to explain all of these languag
Externí odkaz:
http://arxiv.org/abs/2410.01243
This paper introduces a federated learning framework that enables over-the-air computation via digital communications, using a new joint source-channel coding scheme. Without relying on channel state information at devices, this scheme employs lattic
Externí odkaz:
http://arxiv.org/abs/2409.06343
Large language models (LLMs) have exhibited impressive capabilities in various domains, particularly in general language understanding. However these models, trained on massive text data, may not be finely optimized for specific tasks triggered by in
Externí odkaz:
http://arxiv.org/abs/2407.11780
We consider the fractional influence maximization problem, i.e., identifying users on a social network to be incentivized with potentially partial discounts to maximize the influence on the network. The larger the discount given to a user, the higher
Externí odkaz:
http://arxiv.org/abs/2407.05669
Quantum memory systems are vital in quantum information processing for dependable storage and retrieval of quantum states. Inspired by classical reliability theories that synthesize reliable computing systems from unreliable components, we formalize
Externí odkaz:
http://arxiv.org/abs/2406.05599
Publikováno v:
The 2nd Workshop on Cross-Cultural Considerations in NLP (2024)
Multi-agent AI systems can be used for simulating collective decision-making in scientific and practical applications. They can also be used to introduce a diverse group discussion step in chatbot pipelines, enhancing the cultural sensitivity of the
Externí odkaz:
http://arxiv.org/abs/2405.03862
Autor:
Yu, Haizi, Varshney, Lav R.
Data-driven artificial intelligence (AI) techniques are becoming prominent for learning in support of data compression, but are focused on standard problems such as text compression. To instead address the emerging problem of semantic compression, we
Externí odkaz:
http://arxiv.org/abs/2404.03131
This paper introduces a universal federated learning framework that enables over-the-air computation via digital communications, using a new joint source-channel coding scheme. Without relying on channel state information at devices, this scheme empl
Externí odkaz:
http://arxiv.org/abs/2403.01023
Autor:
Wu, Xinbo, Varshney, Lav R.
Even though large language models (LLMs) have demonstrated remarkable capability in solving various natural language tasks, the capability of an LLM to follow human instructions is still a concern. Recent works have shown great improvements in the in
Externí odkaz:
http://arxiv.org/abs/2402.12151