Related papers: Shaking the foundations: delusions in sequence mod…

The abundance of process operating data in modern industries, along with the rapid advancement of learning techniques, has led to a paradigm shift towards data-centric analysis and control. However, integrating machine learning with control…

One of the long-standing goals in optimisation and constraint programming is to describe a problem in natural language and automatically obtain an executable, efficient model. Large language models appear to bring this vision closer,…

Language models have demonstrated remarkable performance in solving reasoning tasks; however, even the strongest models still occasionally make reasoning mistakes. Recently, there has been active research aimed at improving reasoning…

Teaching an agent to perform new tasks using natural language can easily be hindered by ambiguities in interpretation. When a teacher provides an instruction to a learner about an object by referring to its features, the learner can…

Learned dynamics models combined with both planning and policy learning algorithms have shown promise in enabling artificial agents to learn to perform many diverse tasks with limited supervision. However, one of the fundamental challenges…

Large language models (LLMs) are increasingly being adopted as the cognitive core of embodied agents. However, inherited hallucinations, which stem from failures to ground user instructions in the observed physical environment, can lead to…

Transformer based models have shown remarkable capabilities in sequence learning across a wide range of tasks, often performing well on specific task by leveraging input-output examples. Despite their empirical success, a comprehensive…

Vision systems to see and reason about the compositional nature of visual scenes are fundamental to understanding our world. The complex relations between objects and their locations, ambiguities, and variations in the real-world…

Large language models exhibit a remarkable capacity for in-context learning, where they learn to solve tasks given a few examples. Recent work has shown that transformers can be trained to perform simple regression tasks in-context. This…

Large language models (LLMs) often exhibit undesirable behaviors, such as hallucinations and sequence repetitions. We propose to view these behaviors as fallbacks that models exhibit under epistemic uncertainty, and investigate the…

We present a data-driven modeling strategy to overcome improperly modeled dynamics for systems exhibiting complex spatio-temporal behaviors. We propose a Deep Learning framework to resolve the differences between the true dynamics of the…

Foundation models can be disruptive for future AI development by scaling up deep learning in terms of model size and training data's breadth and size. These models achieve state-of-the-art performance (often through further adaptation) on a…

Transformer-based language models have achieved impressive success in various natural language processing tasks due to their ability to capture complex dependencies and contextual information using self-attention mechanisms. However, they…

Prediction failures of machine learning models often arise from deficiencies in training data, such as incorrect labels, outliers, and selection biases. However, such data points that are responsible for a given failure mode are generally…

Causal inference, estimating causal effects from observational data, is a fundamental tool in many disciplines. Of particular importance across a variety of domains is the continuous treatment setting, where the variable of intervention has…

Recent breakthroughs in Natural Language Processing (NLP) have been driven by language models trained on a massive amount of plain text. While powerful, deriving supervision from textual resources is still an open question. For example,…

Among the most critical limitations of deep learning NLP models are their lack of interpretability, and their reliance on spurious correlations. Prior work proposed various approaches to interpreting the black-box models to unveil the…

Non-stationary sequences arise naturally in control, forecasting, and decision-making. The data-generating process shifts at unknown times, and models must detect the change, discard or downweight obsolete evidence, and adapt to new…

Large Language Models (LLMs) have achieved remarkable success, where instruction tuning is the critical step in aligning LLMs with user intentions. In this work, we investigate how the instruction tuning adjusts pre-trained models with a…

Intelligent agents must be able to articulate its own uncertainty. In this work, we show that pre-trained sequence models are naturally capable of probabilistic reasoning over exchangeable data points -- forming informed beliefs and…