AboutTopCourses
← heapsort-ai

AI Research

146 items

RESEARCHarXiv CS.LG·4/22/2026

Compile to Compress: Boosting Formal Theorem Provers by Compiler Outputs

This research introduces a novel learning-to-refine framework to address the prohibitive computational cost of Large Language Models (LLMs) in formal theorem proving. By exploiting compiler outputs that compress diverse proof attempts into structured failure modes, the method enables efficient proof exploration and local error correction, significantly amplifying the reasoning capabilities of base provers.

ScalabilityLLMsTheorem ProvingFormal verification
27
RESEARCHarXiv CS.AI·5/6/2026

Programmatic Context Augmentation for LLM-based Symbolic Regression

This paper introduces a novel LLM-based evolutionary search framework for symbolic regression, addressing the limitations of existing methods that rely solely on scalar evaluation metrics. It incorporates programmatic context augmentation to enable code-based data analysis and richer information extraction, aiming to improve the discovery of mathematical expressions.

data analysisSymbolic RegressionAI ResearchLLM
27
RESEARCHarXiv CS.LG·27d ago

Hierarchical Multi-Scale Graph Neural Networks: Scalable Heterophilous Learning with Oversmoothing and Oversquashing Mitigation

The paper introduces Hierarchical Multi-view HAAR (HMH), a novel spectral graph-learning framework designed to address oversmoothing and degree-biased aggregation in GNNs for heterophilous graphs. HMH constructs a soft graph hierarchy and applies learnable spectral filters using sparse, orthonormal Haar bases, achieving near-linear time scalability.

HeterophilyGraph Neural Networksmachine learningSpectral Graph Theory
27
RESEARCHarXiv CS.CL·21d ago

SKG-Eval: Stateful Evaluation of Multi-Turn Dialogue via Incremental Semantic Knowledge Graphs

SKG-Eval addresses the challenge of evaluating multi-turn dialogue systems by modeling dialogue as an evolving Semantic Knowledge Graph (SKG). This framework incrementally updates the graph through structured triple extraction to detect long-range issues like contradiction and inconsistency, offering improved evaluation beyond turn-isolated representations.

Knowledge GraphsNatural Language ProcessingEvaluation Metricsdialogue systems
27
RESEARCHDEV.to AI·15d ago

François Chollet 谈 AGI 未来

François Chollet discusses the future of AGI, predicting its arrival around 2030, and introduces NDI lab's mission to develop a new, "optimal" machine learning paradigm based on symbolic program synthesis. He critiques deep learning's limitations and outlines NDI's high-risk, high-reward strategy for foundational AI advancement.

AGIdeep learningSymbolic AIBenchmarks
27
ARTICLEDEV.to AI·9d ago

Start Here: My AI Memory Research So Far

The author outlines their journey in AI memory research, detailing four stages of discoveries about the functioning and challenges of these systems. They explore memory survival after resets, the importance of correction memory, the relationship between retrieval accuracy and safety, and the crucial distinction between relevance and authority in AI memory.

Memory SystemsInformation RetrievalAI ResearchAI agents
27
RESEARCHDEV.to AI·26d ago

Uncertainty Estimates of Predictions via a General Bias-Variance Decomposition

A new general bias-variance decomposition for strictly proper scoring rules has finally been introduced in an AISTATS 2023 paper by Gruber & Buettner. This advancement provides practical tools for understanding ensemble models, constructing confidence regions, and improving out-of-distribution detection, addressing a long-standing gap in uncertainty estimation.

Bias-Variancemachine learningUncertainty EstimationScoring Rules
27
RESEARCHarXiv CS.CL·5/5/2026

H-Probes: Extracting Hierarchical Structures From Latent Representations of Language Models

This paper introduces H-probes, linear probes designed to extract hierarchical structure, specifically depth and pairwise distance, from the latent representations of large language models. The research shows these probes robustly find low-dimensional subspaces crucial for performance in synthetic tree traversal tasks, generalizing well both within and out-of-domain.

language modelshierarchical reasoningrepresentation learningAI Research
27