Related papers: Fast yet Safe: Early-Exiting with Risk Control

To provide rigorous uncertainty quantification for online learning models, we develop a framework for constructing uncertainty sets that provably control risk -- such as coverage of confidence intervals, false negative rate, or F1 score --…

Emergence in machine learning refers to the spontaneous appearance of complex behaviors or capabilities that arise from the scale and structure of training data and model architectures, despite not being explicitly programmed. We introduce…

Machine learning (ML) inference platforms are tasked with balancing two competing goals: ensuring high throughput given many requests, and delivering low-latency responses to support interactive applications. Unfortunately, existing…

End-to-end trained neural networks (NNs) are a compelling approach to autonomous vehicle control because of their ability to learn complex tasks without manual engineering of rule-based decisions. However, challenging road conditions,…

The natural world often follows a long-tailed data distribution where only a few classes account for most of the examples. This long-tail causes classifiers to overfit to the majority class. To mitigate this, prior solutions commonly adopt…

Over the last several years, end-to-end neural conversational agents have vastly improved in their ability to carry a chit-chat conversation with humans. However, these models are often trained on large datasets from the internet, and as a…

With the rapid advancement of autonomous driving, deploying Vision-Language Models (VLMs) to enhance perception and decision-making has become increasingly common. However, the real-time application of VLMs is hindered by high latency and…

On-device machine learning is becoming a reality thanks to the availability of powerful hardware and model compression techniques. Typically, these models are pretrained on large GPU clusters and have enough parameters to generalise across…

This extended abstract introduces the initial steps taken to develop a system for Rapid Internal Simulation of Knowledge (RISK). RISK aims to enable more transparency in artificial intelligence systems, especially those created by deep…

Large Reasoning Language Models (LRLMs) demonstrate impressive capabilities on complex tasks by utilizing long Chain-of-Thought reasoning. However, they are prone to overthinking, which generates redundant reasoning steps that degrade both…

With the increasing use of neural networks in critical systems, runtime monitoring becomes essential to reject unsafe predictions during inference. Various techniques have emerged to establish rejection scores that maximize the separability…

Early action prediction seeks to anticipate an action before it fully unfolds, but limited visual evidence makes this task especially challenging. We introduce EAST, a simple and efficient framework that enables a model to reason about…

Encoder-decoder transformer models have achieved great success on various vision-language (VL) tasks, but they suffer from high inference latency. Typically, the decoder takes up most of the latency because of the auto-regressive decoding.…

Minimizing the empirical risk is a popular training strategy, but for learning tasks where the data may be noisy or heavy-tailed, one may require many observations in order to generalize well. To achieve better performance under less…

Large Language Models (LLMs) based on transformers achieve cutting-edge results on a variety of applications. However, their enormous size and processing requirements hinder deployment on constrained resources. To enhance efficiency,…

Many online platforms have deployed anti-fraud systems to detect and prevent fraudulent activities. However, there is usually a gap between the time that a user commits a fraudulent action and the time that the user is suspended by the…

Financial markets of emerging economies are vulnerable to extreme and cascading information spillovers, surges, sudden stops and reversals. With this in mind, we develop a new online early warning system (EWS) to detect what is referred to…

A fundamental open challenge in modern LLM scaling is the lack of understanding around emergent capabilities. In particular, language model pretraining loss is known to be highly predictable as a function of compute. However, downstream…

Scaling the test-time compute of large language models has demonstrated impressive performance on reasoning benchmarks. However, existing evaluations of test-time scaling make the strong assumption that a reasoning system should always give…

Search engine ranking pipelines are commonly based on large ensembles of machine-learned decision trees. The tight constraints on query response time recently motivated researchers to investigate algorithms to make faster the traversal of…