Orthros: Phase-Aware Heterogeneous Attention for Efficient Transformers

arXiv:2610.13735 · cs.LG, cs.AI · Submitted 2026-10-09 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-10-09

Updated: 2026-10-09

Code: https://github.com/gkamradt/LLMTest_

Terminology

• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Zoology: Measuring and Improving Recall in Efficient Language Models
• Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes
• Simple linear attention language models balance the recall-throughput tradeoff
• Qwen3-VL Technical Report
• Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models
• Long Code Arena: a Set of Benchmarks for Long-Context Code Models
• Qwen3-Coder-Next Technical Report
• ZeCO: Zero Communication Overhead Sequence Parallelism for Linear Attention
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
• Sliding Window Attention Training for Efficient Large Language Models
• The Llama 3 Herd of Models
• Mamba: Linear-Time Sequence Modeling with Selective State Spaces
• Mistral 7B
• TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension
• MiniMax-01: Scaling Foundation Models with Lightning Attention
• Jamba: A Hybrid Transformer-Mamba Language Model
• Reconstructing KV Caches with Cross-layer Fusion For Enhanced Transformers
• Nemotron-CC-Math: A 133 Billion-Token-Scale High Quality Math Pretraining Dataset
• gpt-oss-120b & gpt-oss-20b Model Card

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: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks