Research ideas

Every idea extracted from recent arXiv mathematics papers — verified and unverified. Click an idea to open its full card; badges show the empirical verdict.

2 ideas found

Status: Mechanism works Solves: Sample efficiency ML: Attention Clear all

✓ Mechanism works 2026

Rooted Motif Positional Encoding

Augment every graph node with a vector of rooted walk and motif densities rather than relying only on degree or Laplacian positional encodings. This should distinguish nodes or communities with identical expected degree but different connectivity profiles, especially in equal-degree stochastic block models and graphs with locally heterogeneous structure.

Useful7/10

Difficulty4/10

Novelty6/10

Architecture Accuracy Sample efficiency Graph nn

Paper: Beyond Degree: Rooted Motif Signatures for Latent Position Identifiability in Graphon Models arXiv:2607.01358

✓ Mechanism works 2026

Conditional-TC Reveal Scheduler

Replace confidence-only masked diffusion decoding with an adaptive scheduler that chooses batches whose unrevealed tokens have low conditional total correlation given the already revealed context. The scheduler should preserve large parallel batches when token predictions are conditionally independent, but split highly dependent tokens into separate rounds to reduce forward-KL error.

Useful7/10

Difficulty6/10

Novelty7/10

Sampling Accuracy Speedup Sample efficiency

Paper: Conditional Total Correlation and the Serial Depth of Adaptive Parallel Sampling arXiv:2608.25505