Related papers: Corrigibility as a Singular Target: A Vision for I…
Modern robotic systems, deployed across domains from industrial automation to domestic assistance, face a critical challenge: executing tasks with precision and adaptability in dynamic, unpredictable environments. To address this, we…
AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks. We call these models foundation models to underscore their…
Foundation models (FMs) have emerged as a transformative paradigm in medical image analysis, offering the potential to provide generalizable, task-agnostic solutions across a wide range of clinical tasks and imaging modalities. Their…
Foundation models are at the forefront of AI research, appealing for their ability to learn from vast datasets and cater to diverse tasks. Yet, their significant computational demands raise issues of environmental impact and the risk of…
Generative foundation models are susceptible to implicit biases that can arise from extensive unsupervised training data. Such biases can produce suboptimal samples, skewed outcomes, and unfairness, with potentially serious consequences.…
As foundation models (FMs) continue to shape the landscape of AI, the in-context learning (ICL) paradigm thrives but also encounters issues such as toxicity, hallucination, disparity, adversarial vulnerability, and inconsistency. Ensuring…
Foundation models are trained on broad data distributions, yielding generalist capabilities that enable many downstream applications but also expand the space of potential misuse and failures. This position paper argues that capability…
As LLM-based systems increasingly operate as agents embedded within human social and technical systems, alignment can no longer be treated as a property of an isolated model, but must be understood in relation to the environments in which…
The fixed parameter tractable (FPT) approach is a powerful tool in tackling computationally hard problems. In this paper, we link FPT results to classic artificial intelligence (AI) techniques to show how they complement each other.…
For an AI's training process to successfully impart a desired goal, it is important that the AI does not attempt to resist the training. However, partially learned goals will often incentivize an AI to avoid further goal updates, as most…
Controllable text generation systems often leverage control codes to direct various properties of the output like style and length. Inspired by recent work on causal inference for NLP, this paper reveals a previously overlooked flaw in…
The rise of foundation models has shifted focus from resource-intensive fine-tuning to prompt engineering, a paradigm that steers model behavior through input design rather than weight updates. While manual prompt engineering faces…
Recent developments in prompt learning of large Vision-Language Models (VLMs) have significantly improved performance in target-specific tasks. However, these prompting methods often struggle to tackle the target-unspecific or generalizable…
In a controllable text generation dataset, there exist unannotated attributes that could provide irrelevant learning signals to models that use it for training and thus degrade their performance. We propose focused prefix tuning(FPT) to…
Model alignment with human preferences is an essential step in making Large Language Models (LLMs) helpful and consistent with human values. It typically consists of supervised fine-tuning (SFT) and reinforcement learning from human…
Adapting to latent confounded shift remains a core challenge in modern AI. This setting is driven by hidden variables that induce spurious correlations between inputs and outputs during training, leading models to rely on non-causal…
To enhance the reproducibility and reliability of deep learning models, we address a critical gap in current training methodologies: the lack of mechanisms that ensure consistent and robust performance across runs. Our empirical analysis…
Despite the numerous advances, reinforcement learning remains away from widespread acceptance for autonomous controller design as compared to classical methods due to lack of ability to effectively tackle the reality gap. The reliance on…
As artificial intelligence (AI) capabilities advance rapidly, frontier models increasingly demonstrate systematic deception and scheming, complying with safety protocols during oversight but defecting when unsupervised. This paper examines…
Recent breakthroughs in generative simulation have harnessed Large Language Models (LLMs) to generate diverse robotic task curricula, yet these open-loop paradigms frequently produce linguistically coherent but physically infeasible goals,…