Related papers: SIERRA: A Modular Framework for Research Automatio…
Scientific discovery increasingly entails long-horizon exploration of complex hypothesis spaces, yet most existing approaches emphasize final performance while offering limited insight into how scientific exploration unfolds over time,…
LLM-based reasoning models have enabled the development of agentic systems that act as co-scientists, assisting in multi-step scientific analysis. However, evaluating these systems is challenging, as it requires realistic, end-to-end…
The performance and generalization of foundation models for interactive systems critically depend on the availability of large-scale, realistic training data. While recent advances in large language models (LLMs) have improved GUI…
MOTIVATION: Microarray technology makes it possible to measure thousands of variables and to compare their values under hundreds of conditions. Once microarray data are quantified, normalized and classified, the analysis phase is…
The classical approach to design a system is based on a deterministic perspective where the assumption is that the system and its environment are fully predictable, and their behaviour is completely known to the designer. Although this…
We envision a future in which autonomous robots conduct scientific experiments in ways that are not only precise and repeatable, but also open, trustworthy, and transparent. To realize this vision, we present two key contributions: a…
The world is filled with articulated objects that are difficult to determine how to use from vision alone, e.g., a door might open inwards or outwards. Humans handle these objects with strategic trial-and-error: first pushing a door then…
The automation of scientific discovery represents a critical milestone in Artificial Intelligence (AI) research. However, existing agentic systems for science suffer from two fundamental limitations: rigid, pre-programmed workflows that…
A hypothesis testing algorithm is replicable if, when run on two different samples from the same distribution, it produces the same output with high probability. This notion, defined by by Impagliazzo, Lei, Pitassi, and Sorell [STOC'22],…
Solving mathematical reasoning problems requires not only accurate access to relevant knowledge but also careful, multi-step thinking. However, current retrieval-augmented models often rely on a single perspective, follow inflexible search…
This thesis develops a system for automatically analyzing and improving dynamic programs, such as those that have driven progress in natural language processing and computer science, more generally, for decades. Finding a correct program…
Trustworthy machine learning is of primary importance to the practical deployment of deep learning models. While state-of-the-art models achieve astonishingly good performance in terms of accuracy, recent literature reveals that their…
The increasing use of Retrieval-Augmented Generation (RAG) systems in various applications necessitates stringent protocols to ensure RAG systems accuracy, safety, and alignment with user intentions. In this paper, we introduce VERA…
We introduce GIER (Gap-driven Iterative Enhancement of Responses), a general framework for improving large language model (LLM) outputs through self-reflection and revision based on conceptual quality criteria. Unlike prompting strategies…
Numerical reasoning over hybrid data containing tables and long texts has recently received research attention from the AI community. To generate an executable reasoning program consisting of math and table operations to answer a question,…
HRA (Human Reliability Analysis) data is crucial for advancing HRA methodologies. however, existing data collection methods lack the necessary granularity, and most approaches fail to capture dynamic features. Additionally, many methods…
Penetration testing, a critical component of cybersecurity, typically requires extensive time and effort to find vulnerabilities. Beginners in this field often benefit from collaborative approaches with the community or experts. To address…
The standard way to estimate the parameters $\Theta_\text{SEIR}$ (e.g., the transmission rate $\beta$) of an SEIR model is to use grid search, where simulations are performed on each set of parameters, and the parameter set leading to the…
Simulation experiments are typically conducted repeatedly during the model development process, for example, to re-validate if a behavioral property still holds after several model changes. Approaches for automatically reusing and…
In order to automate AI research we introduce a full, end-to-end framework, OMEGA: Optimizing Machine learning by Evaluating Generated Algorithms, that starts at idea generation and ends with executable code. Our system combines structured…