Hugging Face Trending Papers
Jun 24
Communicability-Inspired Positional Encoding (CIPE)
Positional encodings (PEs) are essential for Transformers. Yet designing effective PEs for non-Euclidean graphs remains challenging.
Functional Equivalence in Attention: A Comprehensive Study with Applications to Linear Mode Connectivity
arXiv:2606. 17830v1 Announce Type: cross Abstract: Neural network parameter spaces are inherently non-injective, as distinct parameter configurations can realize identical functions through functional equivalence.
Related stories
arXiv Machine Learning
Jun 25
Communicability-Inspired Positional Encoding (CIPE)
arXiv:2606. 25293v1 Announce Type: new Abstract: Positional encodings (PEs) are essential for Transformers.
arXiv Machine Learning
Jul 22
Toward Manifest Relationality in Transformers via Symmetry Reduction
arXiv:2602. 18948v2 Announce Type: replace Abstract: Transformer models contain substantial internal redundancy arising from coordinate-dependent representations and continuous symmetries, in model space and in head space, respectively.
arXiv AI
Jun 26
Rotary Position Encodings for Graphs
arXiv:2509. 22259v4 Announce Type: replace-cross Abstract: We study the extent to which rotary position encodings (RoPE), a recent transformer position encoding algorithm broadly adopted in large language models (LLMs) and vision transformers (ViTs), can be applied to graph-structured data.
arXiv AI
Jun 4
A Unified Geometric Space for Topological Alignment Between Transformer-Based Models and Human Brain Networks
arXiv:2510. 24342v2 Announce Type: replace Abstract: Prior brain-AI alignment studies are typically constrained by specific inputs and tasks, limiting their ability to capture organizational properties across models with different modalities.
arXiv AI
Jun 12
Different Layers, Different Manifolds: Module-Wise Weight-Space Geometry in Transformer Optimization
arXiv:2606. 13276v1 Announce Type: cross Abstract: Weight-space geometry plays a central role in neural network optimization, yet manifold constraints are often applied uniformly across all weight matrices.
arXiv AI
Jun 6
Where does Absolute Position come from in decoder-only Transformers?
arXiv:2606. 06160v1 Announce Type: new Abstract: RoPE-trained transformers distinguish absolute position in their attention patterns, even though RoPE encodes only relative offsets in the inner product.
Hugging Face Trending Papers
Jun 11
Different Layers, Different Manifolds: Module-Wise Weight-Space Geometry in Transformer Optimization
Weight-space geometry plays a central role in neural network optimization, yet manifold constraints are often applied uniformly across all weight matrices. In this work, we ask whether different transformer modules prefer different manifold geometries.
arXiv AI
Jul 15
Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task
arXiv:2510. 18315v2 Announce Type: replace-cross Abstract: We investigate how embedding dimension affects the emergence of an internal "world model" in a transformer trained with reinforcement learning to perform bubble-sort-style adjacent swaps.
arXiv AI
Jun 2
Generic Interpretation Approach for Transformer Models Incorporating Heterogenous Attention Structures
arXiv:2605. 27458v2 Announce Type: replace-cross Abstract: Transformer has significantly propelled the development of artificial intelligence, and certainly the development of agents as well.
arXiv Machine Learning
Jul 14
From Self-Attention to Connection Laplacian: A Unified Operator View of Transformers
arXiv:2607. 10677v1 Announce Type: new Abstract: Self-attention is a ubiquitous primitive in modern sequence models, yet its operator-level geometry is only partially understood.
arXiv Machine Learning
Jun 29
Prism Transformer: Progressive Head Schedules for Hierarchical Attention Processing
arXiv:2606. 27449v1 Announce Type: new Abstract: Multi-head attention conventionally partitions the hidden dimension equally across all heads at every layer, enforcing an identical representational subspace dimension (dh = dmodel/h) throughout the models depth.