🏢 University of Virginia

Recommendation algorithms on UGC platforms face a critical trade-off: prioritizing user satisfaction reduces creator engagement, jeopardizing long-term content diversity. This research introduces a ga…

Pre-trained transformers can provably learn to play games near-optimally using in-context learning, offering theoretical guarantees for both decentralized and centralized settings.

MoD, a novel Mixture of Demonstrations framework, enhances in-context learning by partitioning demonstration pools and employing expert-wise training, achieving state-of-the-art performance.

This paper proposes a novel method to model group actions within autoencoders by learning these actions in the latent space, enhancing model versatility and improving performance in various real-world…

TRIPLE: Efficient prompt optimization using fixed-budget best-arm identification.

E2, a novel regional contrastive learning method, enhances vision-language models for expressive fashion representations by explicitly attending to fashion details with minimal additional parameters, …

This paper presents novel algorithms for linear bandits that are robust to corrupted rewards, achieving minimax optimality and optimal scaling for gap-dependent misspecification, extending to reinforc…

Projected Diffusion Models (PDM) revolutionizes generative modeling by directly incorporating constraints into the sampling process, ensuring high-fidelity outputs that strictly adhere to predefined c…

Popular large language model (LLM)-based time series forecasting methods perform no better than simpler alternatives, often worse, and require vastly more compute.