Related papers: Embodied Science: Closing the Discovery Loop with …
In modern data-driven science, reproducibility and reusability are key challenges. Scientists are well skilled in the process from data to publication. Although some publication channels require source code and data to be made accessible,…
Embodied AI models often employ off the shelf vision backbones like CLIP to encode their visual observations. Although such general purpose representations encode rich syntactic and semantic information about the scene, much of this…
Scientific research is being reshaped by AI systems that move beyond isolated assistance toward longer-horizon workflows spanning literature grounding, hypothesis generation, experimentation, validation, reporting, and revision. This shift…
A long-standing challenge in economics lies not in the lack of intuition, but in the difficulty of translating intuitive insights into verifiable research. To address this challenge, we introduce AgentEconomist, an end-to-end interactive…
We study lifelong visual perception in an embodied setup, where we develop new models and compare various agents that navigate in buildings and occasionally request annotations which, in turn, are used to refine their visual perception…
Autonomous agents powered by large language models (LLMs) promise to accelerate scientific discovery end-to-end, but rigorously evaluating their capacity for verifiable discovery remains a central challenge. Existing benchmarks face a…
Text embeddings have become central to computational social science and psychology, enabling scalable measurement of meaning and mixed-method inference. Yet most representation learning is optimized and evaluated for prediction and…
Human-robot interaction is increasingly moving toward multi-robot, socially grounded environments. Existing systems struggle to integrate multimodal perception, embodied expression, and coordinated decision-making in a unified framework.…
Embodied AI is widely recognized as a cornerstone of artificial general intelligence (AGI) because it involves controlling embodied agents to perform tasks in the physical world. Building on the success of large language models (LLMs) and…
Large language model (LLM)-based systems are increasingly deployed to conduct scientific research autonomously, yet whether their reasoning adheres to the epistemic norms that make scientific inquiry self-correcting is poorly understood.…
Embodied AI (EAI) agents continuously interact with the physical world, generating vast, heterogeneous multimodal data streams that traditional management systems are ill-equipped to handle. In this survey, we first systematically evaluate…
Scientific discovery is constrained not only by what is true, but by what is cognitively available to the researchers currently exploring a field. Many directions are coherent in light of the literature yet unlikely to be proposed because…
With the advent of large multimodal language models, science is now at a threshold of an AI-based technological transformation. An emerging ecosystem of models and tools aims to support researchers throughout the scientific lifecycle,…
A suite of impressive scientific discoveries have been driven by recent advances in artificial intelligence. These almost all result from training flexible algorithms to solve difficult optimization problems specified in advance by teams of…
Scientific Machine Learning (SciML) integrates data-driven inference with physical modeling to solve complex problems in science and engineering. However, the design of SciML architectures, loss formulations, and training strategies remains…
Recent autonomous LLM agents have demonstrated end-to-end automation of machine-learning research. Real-world physical science is intrinsically harder, requiring deep reasoning bounded by physical truth and, because real systems are too…
Artificial intelligence (AI) methods are poised to revolutionize intellectual work, with generative AI enabling automation of text analysis, text generation, and simple decision making or reasoning. The impact to science is only just…
While natural language understanding (NLU) is advancing rapidly, today's technology differs from human-like language understanding in fundamental ways, notably in its inferior efficiency, interpretability, and generalization. This work…
Recent advances in RAG have shifted toward an agentic paradigm, where LLMs interact with retrieval systems over multiple turns and iteratively refine queries based on intermediate results. At the same time, LLMs have demonstrated a strong…
Traditionally, theory and practice of Cognitive Control are linked via literature reviews by human domain experts. This approach, however, is inadequate to track the ever-growing literature. It may also be biased, and yield redundancies and…