English
Related papers

Related papers: Semi-Autonomous Mathematics Discovery with Gemini:…

200 papers

Anomaly detection has been considered under several extents of prior knowledge. Unsupervised methods do not require any labelled data, whereas semi-supervised methods leverage some known anomalies. Inspired by mixture-of-experts models and…

Machine Learning · Computer Science 2022-10-14 J. -P. Schulze , P. Sperl , K. Böttinger

Artificial Intelligence (AI) is beginning to transform the research process by automating the discovery of new solutions. This shift depends on the availability of reliable verifiers, which AI-driven approaches require to validate candidate…

A pseudo independent (PI) model is a probabilistic domain model (PDM) where proper subsets of a set of collectively dependent variables display marginal independence. PI models cannot be learned correctly by many algorithms that rely on a…

Artificial Intelligence · Computer Science 2013-02-08 Jun Hu , Yang Xiang

Large Language Models (LLMs) have demonstrated impressive capabilities in natural language and code generation, and are increasingly deployed as automatic judges of model outputs and learning activities. Yet, their behavior on structured…

Computation and Language · Computer Science 2025-11-25 H. M. Shadman Tabib , Jaber Ahmed Deedar

In this paper, we study a general semi-random version of the planted independent set problem in a model initially proposed by Feige and Kilian, which has a large proportion of adversarial edges. We give a new deterministic algorithm that…

Data Structures and Algorithms · Computer Science 2019-10-31 Theo McKenzie , Hermish Mehta , Luca Trevisan

PDEs are central to scientific and engineering modeling, yet designing accurate numerical solvers typically requires substantial mathematical expertise and manual tuning. Recent neural network-based approaches improve flexibility but often…

Artificial Intelligence · Computer Science 2026-02-20 Jianda Du , Youran Sun , Haizhao Yang

Traditional evaluation metrics like BLEU and ROUGE fall short when capturing the nuanced qualities of generated text, particularly when there is no single ground truth. In this paper, we explore the potential of Large Language Models…

Computation and Language · Computer Science 2024-12-13 Manav Chaudhary , Harshit Gupta , Savita Bhat , Vasudeva Varma

Language model evaluations often fail to characterize consequential failure modes, forcing experts to inspect outputs and build new benchmarks. We introduce task elicitation, a method that automatically builds new evaluations to profile…

Computation and Language · Computer Science 2025-09-29 Davis Brown , Prithvi Balehannina , Helen Jin , Shreya Havaldar , Hamed Hassani , Eric Wong

Background: Academic search engines (i.e., digital libraries and indexers) play an increasingly important role in systematic reviews however these engines do not seem to effectively support such reviews, e.g., researchers confront usability…

Software Engineering · Computer Science 2022-11-02 Zheng Li , Austen Rainer

Recent advances in AI have catalyzed the adoption of intelligent educational tools, yet many semantic retrieval systems remain ill-suited to the unique linguistic and structural characteristics of academic content. This study presents two…

Computation and Language · Computer Science 2025-05-09 Ramteja Sajja , Yusuf Sermet , Ibrahim Demir

Two novel deep hybrid architectures, the Deep Hybrid Boltzmann Machine and the Deep Hybrid Denoising Auto-encoder, are proposed for handling semi-supervised learning problems. The models combine experts that model relevant distributions at…

Machine Learning · Computer Science 2016-01-19 Alexander G. Ororbia , C. Lee Giles , David Reitter

In the words of the esteemed mathematician Paul Erd\"os, the mathematician's task is to \emph{prove and conjecture}. These two processes form the bedrock of all mathematical endeavours, and in the recent years, the mathematical community…

Combinatorics · Mathematics 2023-07-18 Randy Davila

This paper explores role engineering as an effective paradigm for customizing Large Language Models (LLMs) into specialized AI tutors for physics education. We demonstrate this methodology by designing a Socratic physics problem-solving…

Physics Education · Physics 2025-10-28 Eugenio Tufino , Bor Gregorcic

The rising cost of acquiring supervised data has driven significant interest in self-improvement for large language models (LLMs). Straightforward unsupervised signals like majority voting have proven effective in generating pseudo-labels…

Computation and Language · Computer Science 2026-04-01 Chunyang Jiang , Yonggang Zhang , Yiyang Cai , Chi-Min Chan , Yulong Liu , Mingming Chen , Wei Xue , Yike Guo

The main drawback of using generative AI models for advanced mathematics is that these models are not primarily logical reasoning engines. However, Large Language Models, and their refinements, can pick up on patterns in higher mathematics…

History and Overview · Mathematics 2025-12-19 Lisa Carbone

State-of-the-art (SOTA) LLMs have progressed from struggling on proof-based Olympiad problems to solving most of the IMO 2025 problems, with leading systems reportedly handling 5 of 6 problems. Given this progress, we assess how well these…

Large-enrollment university courses face persistent challenges in providing timely and scalable instructional support. While generative AI holds promise, its effective use depends on reliability and pedagogical alignment. We present a…

Computers and Society · Computer Science 2026-03-31 Jérémy Barghorn , Anna Sotnikova , Sacha Friedli , Antoine Bosselut

This thesis investigates the central role of homomorphism problems (structure-preserving maps) in two complementary domains: database querying over finite, graph-shaped data, and constraint solving over (potentially infinite) structures.…

Logic in Computer Science · Computer Science 2025-10-10 Rémi Morvan

Predicting attention regions of interest is an important yet challenging task for self-driving systems. Existing methodologies rely on large-scale labeled traffic datasets that are labor-intensive to obtain. Besides, the huge domain gap…

Computer Vision and Pattern Recognition · Computer Science 2023-07-18 Pengfei Zhu , Mengshi Qi , Xia Li , Weijian Li , Huadong Ma

We report the performance of Aletheia (Feng et al., 2026b), a mathematics research agent powered by Gemini 3 Deep Think, on the inaugural FirstProof challenge. Within the allowed timeframe of the challenge, Aletheia autonomously solved 6…