Skip to main content
arXiv is now an independent nonprofit! Learn more

Showing 1–7 of 7 results for author: Sheng, A

Searching in archive cs. Search in all archives.
.
  1. arXiv:2605.00758  [pdf, ps, other

    physics.soc-ph cs.GT

    Optimal network structure for collective performance with strategic information sharing

    Authors: Ye Wang, Andrea Civilini, Anzhi Sheng, Xiaojie Chen, Long Wang, Vito Latora

    Abstract: Information sharing between individuals is crucial to improve performance in collective tasks. However, in a competitive world, individuals may be reluctant to share information with the others, and it is still unclear how the presence of strategic behaviors affects the collective performance of a group. In this study, we introduce an evolutionary game modeling the dynamics of individual behaviors… ▽ More

    Submitted 1 May, 2026; originally announced May 2026.

  2. arXiv:2603.01509  [pdf, ps, other

    cs.CV cs.AI

    Retrieval, Refinement, and Ranking for Text-to-Video Generation via Prompt Optimization and Test-Time Scaling

    Authors: Zillur Rahman, Alex Sheng, Cristian Meo

    Abstract: While large-scale datasets have driven significant progress in Text-to-Video (T2V) generative models, these models remain highly sensitive to input prompts, demonstrating that prompt design is critical to generation quality. Current methods for improving video output often fall short: they either depend on complex, post-editing models, risking the introduction of artifacts, or require expensive fi… ▽ More

    Submitted 2 March, 2026; originally announced March 2026.

    Comments: 2026 ICLR TTU Workshop

  3. arXiv:2404.11964  [pdf, ps, other

    cs.AI

    From Language Models to Practical Self-Improving Computer Agents

    Authors: Alex Sheng

    Abstract: We develop a simple and straightforward methodology to create AI computer agents that can carry out diverse computer tasks and self-improve by developing tools and augmentations to enable themselves to solve increasingly complex tasks. As large language models (LLMs) have been shown to benefit from non-parametric augmentations, a significant body of recent work has focused on developing software t… ▽ More

    Submitted 18 April, 2024; originally announced April 2024.

    MSC Class: 68T01 ACM Class: I.2.0

  4. arXiv:2206.06705  [pdf, other

    cs.CL cs.LG

    Task Transfer and Domain Adaptation for Zero-Shot Question Answering

    Authors: Xiang Pan, Alex Sheng, David Shimshoni, Aditya Singhal, Sara Rosenthal, Avirup Sil

    Abstract: Pretrained language models have shown success in various areas of natural language processing, including reading comprehension tasks. However, when applying machine learning methods to new domains, labeled data may not always be available. To address this, we use supervised pretraining on source-domain data to reduce sample complexity on domain-specific downstream tasks. We evaluate zero-shot perf… ▽ More

    Submitted 14 June, 2022; originally announced June 2022.

    Comments: NAACL 2022 Deep Learning for Low-Resource NLP Workshop Paper

    MSC Class: 68T50 ACM Class: I.2.7

  5. arXiv:2205.00167  [pdf, other

    cs.AI cs.LG

    Self-Programming Artificial Intelligence Using Code-Generating Language Models

    Authors: Alex Sheng, Shankar Padmanabhan

    Abstract: Recent progress in large-scale language models has enabled breakthroughs in previously intractable computer programming tasks. Prior work in meta-learning and neural architecture search has led to substantial successes across various task domains, spawning myriad approaches for algorithmically optimizing the design and learning dynamics of deep learning models. At the intersection of these researc… ▽ More

    Submitted 2 February, 2023; v1 submitted 30 April, 2022; originally announced May 2022.

    MSC Class: 68T07 ACM Class: I.2.0

  6. Efficient Distributed Learning in Stochastic Non-cooperative Games without Information Exchange

    Authors: Haidong Li, Anzhi Sheng, Yijie Peng, Long Wang

    Abstract: In this work, we study stochastic non-cooperative games, where only noisy black-box function evaluations are available to estimate the cost function for each player. Since each player's cost function depends on both its own decision variables and its rivals' decision variables, local information needs to be exchanged through a center/network in most existing work for seeking the Nash equilibrium.… ▽ More

    Submitted 16 February, 2022; v1 submitted 26 January, 2022; originally announced January 2022.

  7. Distributed Evolution Strategies Using TPUs for Meta-Learning

    Authors: Alex Sheng, Derek He

    Abstract: Meta-learning traditionally relies on backpropagation through entire tasks to iteratively improve a model's learning dynamics. However, this approach is computationally intractable when scaled to complex tasks. We propose a distributed evolutionary meta-learning strategy using Tensor Processing Units (TPUs) that is highly parallel and scalable to arbitrarily long tasks with no increase in memory c… ▽ More

    Submitted 31 December, 2021; originally announced January 2022.

    Comments: Published in Proceedings of the 2020 IEEE Symposium Series on Computational Intelligence (SSCI)

    Journal ref: 2020 IEEE Symposium Series on Computational Intelligence (SSCI), 2020, pp. 721-728