Related papers: Automated Capability Discovery via Foundation Mode…

Molecular property prediction and generative design via deep learning models has been the subject of intense research given its potential to accelerate development of new, high-performance materials. More recently, these workflows have been…

Benchmarks are often used as a standard to understand LLM capabilities in different domains. However, aggregate benchmark scores provide limited insight into compositional skill gaps of LLMs and how to improve them. To make these weaknesses…

Over the last decade, research on automated parameter tuning, often referred to as automatic algorithm configuration (AAC), has made significant progress. Although the usefulness of such tools has been widely recognized in real world…

Foundation models are premised on the idea that sequence prediction can uncover deeper domain understanding, much like how Kepler's predictions of planetary motion later led to the discovery of Newtonian mechanics. However, evaluating…

Latent world models allow agents to reason about complex environments with high-dimensional observations. However, adapting to new environments and effectively leveraging previous knowledge remain significant challenges. We present…

In the rapidly evolving field of artificial intelligence, the ability to harness and integrate knowledge across various domains stands as a paramount challenge and opportunity. This study introduces a novel approach to cross-domain…

Generalized category discovery (GCD) is a recently proposed open-world task. Given a set of images consisting of labeled and unlabeled instances, the goal of GCD is to automatically cluster the unlabeled samples using information…

Recent advances in Large Language Models (LLMs) have significantly enhanced their capabilities, highlighting the need for comprehensive evaluation frameworks that extend beyond task-specific benchmarks. However, existing benchmarks often…

Comprehensive evaluation of the recommendation capabilities of existing foundation models across diverse datasets and domains is essential for advancing the development of recommendation foundation models. In this study, we introduce…

Accurate estimation of uncertainty in deep learning is critical for deploying models in high-stakes domains such as medical diagnosis and autonomous decision-making, where overconfident predictions can lead to harmful outcomes. In practice,…

Inferring causal relationships as directed acyclic graphs (DAGs) is an important but challenging problem. Differentiable Causal Discovery (DCD) is a promising approach to this problem, framing the search as a continuous optimization. But…

In recent years, AI models that mine intrinsic patterns from molecular structures and protein sequences have shown promise in accelerating drug discovery. However, these methods partly lag behind real-world pharmaceutical approaches of…

Trajectory Prediction (TP) is an important research topic in computer vision and robotics fields. Recently, many stochastic TP models have been proposed to deal with this problem and have achieved better performance than the traditional…

The vision of a broadly capable and goal-directed agent, such as an Internet-browsing agent in the digital world and a household humanoid in the physical world, has rapidly advanced, thanks to the generalization capability of foundation…

Rapid advances in large language models and agentic AI are driving the emergence of the Internet of Agents (IoA), a paradigm where billions of autonomous software and embodied agents interact, coordinate, and collaborate to accomplish…

Given the remarkable performance of Large Language Models (LLMs), an important question arises: Can LLMs conduct human-like scientific research and discover new knowledge, and act as an AI scientist? Scientific discovery is an iterative…

Uncovering the underlying causal mechanisms of complex real-world systems remains a significant challenge, as these systems often entail high data collection costs and involve unknown interventions. We introduce MetaCaDI, the first…

As artificial intelligence (AI) models are scaled up, new capabilities can emerge unintentionally and unpredictably, some of which might be dangerous. In response, dangerous capabilities evaluations have emerged as a new risk assessment…

Deep learning models, though having achieved great success in many different fields over the past years, are usually data hungry, fail to perform well on unseen samples, and lack of interpretability. Various prior knowledge often exists in…

Reconstructing accurate causal models of dynamic systems from time-series of sensor data is a key problem in many real-world scenarios. In this paper, we present an overview based on our experience about practical challenges that the causal…