相关论文: NOVA: Fundamental Limits of Knowledge Discovery Th…
Knowledge compilation studies the trade-off between succinctness and efficiency of different representation languages. For many languages, there are known strong lower bounds on the representation size, but recent work shows that, for some…
Reasoning models often outperform smaller models but at 3--5$\times$ higher cost and added latency. We present entropy-guided refinement: a lightweight, test-time loop that uses token-level uncertainty to trigger a single, targeted…
Existing automated research systems operate as stateless, linear pipelines -- generating outputs without maintaining any persistent understanding of the research landscape they navigate. They process papers sequentially, propose ideas…
Nigam et al. reported a genetic algorithm (GA) utilizing the SELFIES representation and also propose an adaptive, neural network-based penalty that is supposed to improve the diversity of the generated molecules. The main claims of the…
Although different learning systems are coordinated to afford complex behavior, little is known about how this occurs. This article describes a theoretical framework that specifies how complex behaviors that might be thought to require…
Artificial neural networks thrive in solving the classification problem for a particular rigid task, acquiring knowledge through generalized learning behaviour from a distinct training phase. The resulting network resembles a static entity…
Assessing originality in AI research is arguably the most consequential yet least reliable step in peer review. Reviewer judgments of originality remain opaque, inconsistent, and dependent on comparisons to prior work that are often…
Generative AI is entering research, education, and professional work faster than current governance frameworks can specify how AI-assisted outputs should be judged in learning-intensive settings. The central problem is proxy failure: a…
Deep NLP models have been shown to learn spurious correlations, leaving them brittle to input perturbations. Recent work has shown that counterfactual or contrastive data -- i.e. minimally perturbed inputs -- can reveal these weaknesses,…
Incremental learning suffers from two challenging problems; forgetting of old knowledge and intransigence on learning new knowledge. Prediction by the model incrementally learned with a subset of the dataset are thus uncertain and the…
While previous AI Scientist systems can generate novel findings, they often lack the focus to produce scientifically valuable contributions that address pressing human-defined challenges. We introduce DeepScientist, a system designed to…
Incorporating specific knowledge into large language models via retrieval-augmented generation (RAG) is a widespread technique that fuels many of today's industry AI applications. A fundamental problem is to assess if the context retrieved…
Automatic test generation aims to save developers time and effort by producing test suites with reasonably high coverage and fault detection. However, the focus of search-based generation tools in maximizing coverage leaves other…
A fundamental question in the conjunction of information theory, biophysics, bioinformatics and thermodynamics relates to the principles and processes that guide the development of natural intelligence in natural environments where…
We consider the optimal value of information (VoI) problem, where the goal is to sequentially select a set of tests with a minimal cost, so that one can efficiently make the best decision based on the observed outcomes. Existing algorithms…
We describe a set of techniques to generate queries automatically based on one or more ingested, input corpuses. These queries require no a priori domain knowledge, and hence no human domain experts. Thus, these auto-generated queries help…
In high-stakes domains like legal question-answering, the accuracy and trustworthiness of generative AI systems are of paramount importance. This work presents a comprehensive benchmark of various methods to assess the groundedness of…
Background: Exploration of the physical environment is an indispensable precursor to information acquisition and knowledge consolidation for living organisms. Yet, current artificial intelligence models lack these autonomy capabilities…
An AI agent might surprisingly find she has reached an unknown state which she has never been aware of -- an unknown unknown. We mathematically ground this scenario in reinforcement learning: an agent, after taking an action calculated from…
As datasets grow richer, an important challenge is to leverage the full features in the data to maximize the number of useful discoveries while controlling for false positives. We address this problem in the context of multiple hypotheses…