arXiv AI
Distance-Aware Attention and Wall-Distance Expert Routing for Transformer-Based 3D Flow Prediction
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Aug 18
RETO: A Rotary-Enhanced Transformer Operator for High-Fidelity Prediction of Automotive Aerodynamics
arXiv:2605. 00062v3 Announce Type: replace-cross Abstract: Rapid aerodynamic evaluation is crucial for modern vehicle design, yet existing neural operators struggle to capture intricate spatial correlations.
arXiv AI
Jun 2
From Layers to Submodules: Rethinking Granularity in Replacement-Based LLM Compression
arXiv:2606. 02559v1 Announce Type: cross Abstract: Post-training compression of Large Language Models (LLMs) removes entire architectural components, either deleting them or replacing them with fitted modules.
arXiv Machine Learning
Jul 13
Training, Reading, and Editing Legible Transformers
arXiv:2607. 08946v1 Announce Type: new Abstract: A transformer can be built from operators that are legible by construction -- bounded, named units that read as fuzzy set operations rather than dense activations -- but legibility must be pressed for during training, and the pressure has a failure mode.
arXiv Machine Learning
Aug 12
Off-Axis, On Purpose: Where a Transformer Computes Concepts and Why it Does So
arXiv:2608. 10251v1 Announce Type: cross Abstract: A transformer's answer lives on one axis: the direction its unembedding reads.
arXiv Machine Learning
Sep 15
Disentangling Representation Evolution in Transformers through Directional Decomposition
arXiv:2609.15975v1 Announce Type: cross Abstract: Transformer representations evolve through learned additive transformations that either preserve their current direction or redirect it. We study thi...
Hugging Face Trending Papers
3d ago
Learning Functional Subspaces for Neural Network Compression
Modern transformers pair impressive capabilities with substantial memory and compute demands. Low-rank weight factorization reduces both while keeping the matrices dense, and thus efficient on standar...