相关论文: UAT-LITE: Inference-Time Uncertainty-Aware Attenti…

Deep learning-based trajectory prediction models have demonstrated promising capabilities in capturing complex interactions. However, their out-of-distribution generalization remains a significant challenge, particularly due to unbalanced…

Numerous real-world decisions rely on machine learning algorithms and require calibrated uncertainty estimates. However, modern methods often yield overconfident, uncalibrated predictions. The dominant approach to quantifying the…

Generating probabilistic forecasts of potential outcomes and individual treatment effects (ITE) is essential for risk-aware decision-making in domains such as healthcare, policy, marketing, and finance. We propose two novel methods: the…

We propose a novel framework for producing a class of parameter and compute efficient models called AttentionLitesuitable for resource-constrained applications. Prior work has primarily focused on optimizing models either via knowledge…

How much information do NLP tasks really need from a transformer's attention mechanism at application-time (inference)? From recent work, we know that there is sparsity in transformers and that the floating-points within its computation can…

We introduce the Byte Latent Transformer (BLT), a new byte-level LLM architecture that, for the first time, matches tokenization-based LLM performance at scale with significant improvements in inference efficiency and robustness. BLT…

Introduction: Timely care in a specialised neuro-intensive therapy unit (ITU) reduces mortality and hospital stays, with planned admissions being safer than unplanned ones. However, post-operative care decisions remain subjective. This…

In recent times, BERT-based models have been extremely successful in solving a variety of natural language processing (NLP) tasks such as reading comprehension, natural language inference, sentiment analysis, etc. All BERT-based…

Replicating causal estimates across different cohorts is crucial for increasing the integrity of epidemiological studies. However, strong assumptions regarding unmeasured confounding and effect modification often hinder this goal. By…

Recently, test-time adaptation has garnered attention as a method for tuning models without labeled data. The conventional modus operandi for adapting pre-trained vision-language models (VLMs) during test-time primarily focuses on tuning…

When deployed for risk-sensitive tasks, deep neural networks must include an uncertainty estimation mechanism. Here we examine the relationship between deep architectures and their respective training regimes, with their corresponding…

Large Language Models (LLMs) have emerged as a pivotal research area, yet the attention module remains a critical bottleneck in LLM inference, even with techniques like KVCache to mitigate redundant computations. While various top-$k$…

In educational applications, Knowledge Tracing (KT), the problem of accurately predicting students' responses to future questions by summarizing their knowledge states, has been widely studied for decades as it is considered a fundamental…

Temporal logic inference is the process of extracting formal descriptions of system behaviors from data in the form of temporal logic formulas. The existing temporal logic inference methods mostly neglect uncertainties in the data, which…

Pre-trained Transformer models such as BERT have shown great success in a wide range of applications, but at the cost of substantial increases in model complexity. Quantization-aware training (QAT) is a promising method to lower the…

Transformers have achieved extraordinary success in modern machine learning due to their excellent ability to handle sequential data, especially in next-token prediction (NTP) tasks. However, the theoretical understanding of their…

Pretrained knowledge memorized in LLMs raises critical concerns over safety and privacy, which has motivated LLM Unlearning as a technique for selectively removing the influences of undesirable knowledge. Existing approaches, rooted in…

Uncertainty-quantification methods are applied to estimate the confidence of deep-neural-networks classifiers over their predictions. However, most widely used methods are known to be overconfident. We address this problem by developing an…

The reliable operation of modern power grids requires probabilistic load forecasts with well-calibrated uncertainty estimates. However, existing deep learning models produce overconfident point predictions that fail catastrophically under…

Vision Transformer (ViT) has emerged as a competitive alternative to convolutional neural networks for various computer vision applications. Specifically, ViT multi-head attention layers make it possible to embed information globally across…