![[2606.04366] MeshTok: Efficient Multi-Scale Tokenization for Scalable PDE Transformers](/static/img/curated/desks/afbytes-tech.png)
[2606.04366] MeshTok: Efficient Multi-Scale Tokenization for Scalable PDE Transformers
Abstract page for arXiv paper 2606.04366: MeshTok: Efficient Multi-Scale Tokenization for Scalable PDE Transformers
America Forever Bytes
transformers · AFBytes
Technology
transformers
Recent coverage
[2606.04032] Do Transformers Need Three Projections? Systematic Study of QKV Variants
Abstract page for arXiv paper 2606.04032: Do Transformers Need Three Projections? Systematic Study of QKV Variants
[2606.04405] Low-Rank Decay for Grokking in Scale-Invariant Transformers: A Spectral-Geometric View
Abstract page for arXiv paper 2606.04405: Low-Rank Decay for Grokking in Scale-Invariant Transformers: A Spectral-Geometric View
[2606.04752] An Empirical Audit of Input Encoders for Multi-Channel Signal Transformers
Abstract page for arXiv paper 2606.04752: An Empirical Audit of Input Encoders for Multi-Channel Signal Transformers
[2505.17315] Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning
Abstract page for arXiv paper 2505.17315: Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning
[2510.24342] A Unified Geometric Space for Topological Alignment Between Transformer-Based Models and Human Brain Networks
Abstract page for arXiv paper 2510.24342: A Unified Geometric Space for Topological Alignment Between Transformer-Based Models and Human Brain Networks
[2606.00114] Recursive Vision Transformer with Dynamic Depth and Width Adjustment for Resource-Efficient Image Semantic Communication
Abstract page for arXiv paper 2606.00114: Recursive Vision Transformer with Dynamic Depth and Width Adjustment for Resource-Efficient Image Semantic Communicati...
[2511.16886] Latent Reasoning in TRMs is Secretly a Policy Improvement Operator
Abstract page for arXiv paper 2511.16886: Latent Reasoning in TRMs is Secretly a Policy Improvement Operator
[2606.01532] Rethinking the Role of Positional Encoding: Sliding-Window Transformers without PE Remain Turing Complete
Abstract page for arXiv paper 2606.01532: Rethinking the Role of Positional Encoding: Sliding-Window Transformers without PE Remain Turing Complete
[2605.31204] Probabilistic Precipitation Nowcasting with Rectified Flow Transformers
Abstract page for arXiv paper 2605.31204: Probabilistic Precipitation Nowcasting with Rectified Flow Transformers
[2605.31367] Trading Complexity for Expressivity Through Structured Generalized Linear Token Mixing
Abstract page for arXiv paper 2605.31367: Trading Complexity for Expressivity Through Structured Generalized Linear Token Mixing
[2605.30523] Revisiting Padded Transformer Expressivity: Which Architectural Choices Matter and Which Don't
Abstract page for arXiv paper 2605.30523: Revisiting Padded Transformer Expressivity: Which Architectural Choices Matter and Which Don't
[2605.29634] Relational Rank Geometry in Transformers: Detecting and Steering Hidden-State Relation Frames
Abstract page for arXiv paper 2605.29634: Relational Rank Geometry in Transformers: Detecting and Steering Hidden-State Relation Frames
[2605.29754] Benchmarking Positional Encoding Strategies for Transformer-Based EEG Foundation Models
Abstract page for arXiv paper 2605.29754: Benchmarking Positional Encoding Strategies for Transformer-Based EEG Foundation Models
One of the Most Valuable G1 Transformers Ever Returns to Auction – Can It Beat the Record?
The Transformers franchise continues to set new records with its merchandise and collectibles, and this latest sale is hard to beat.
[2605.27458] Generic Interpretation Approach for Transformer Models Incorporating Heterogenous Attention Structures
Abstract page for arXiv paper 2605.27458: Generic Interpretation Approach for Transformer Models Incorporating Heterogenous Attention Structures
[2605.28592] PLS in the Mirror of Self-Attention
Abstract page for arXiv paper 2605.28592: PLS in the Mirror of Self-Attention
[2605.28600] Transformers Provably Learn to Internalize Chain-of-Thought
Abstract page for arXiv paper 2605.28600: Transformers Provably Learn to Internalize Chain-of-Thought
[2605.28075] Measure-to-measure Regression with Transformers
Abstract page for arXiv paper 2605.28075: Measure-to-measure Regression with Transformers