PermuFormer: Multi-Task Pretraining for Permutation Representation in Algebraic Combinatorics
cs.LG, math.CO
Submitted: 2026-09-21
Updated: 2026-09-21
Comments: 33 pages. Comments welcome
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Billion-Scale Graph Foundation Models
- Even with AI, Bijection Discovery is Still Hard: The Opportunities and Challenges of OpenEvolve for Novel Bijection Construction
- Machine Learning meets Algebraic Combinatorics: A Suite of Datasets Capturing Research-level Conjecturing Ability in Pure Mathematics
- STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Why are Sensitive Functions Hard for Transformers?
- Strategies for Pre-training Graph Neural Networks
- Discovering a Zeta Map Algorithm on Dyck Paths via Mechanistic Interpretability
- OpenAI o1 System Card
- Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task
- Goedel-Prover: A Frontier Model for Open-Source Automated Theorem Proving
- Graph Foundation Models: Concepts, Opportunities and Challenges
- UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
- IntSeqBERT: Learning Arithmetic Structure in OEIS via Modulo-Spectrum Embeddings
- Progress measures for grokking via mechanistic interpretability
- Learning the symmetric group: large from small
- Does Representation Matter? Exploring Intermediate Layers in Large Language Models
- Grokking Group Multiplication with Cosets
- What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models
- Graph Foundation Models: A Comprehensive Survey
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks