ARM: Attention with Routed-Memory for Learnable Sparse Control
cs.LG, cs.AI
Submitted: 2026-09-21
Updated: 2026-09-21
Comments: Accepted to the Forty-third International Conference on Machine Learning (ICML) 2026. First two authors contributed equally
Code: https://github.com/NVIDIA/RULERhttps:
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Longformer: The Long-Document Transformer
- Think you have Solved Direct-Answer Question Answering? Try ARC-DA, the Direct-Answer AI2 Reasoning Challenge
- Command A: An Enterprise-Ready Large Language Model
- Palu: Compressing KV-Cache with Low-Rank Projection
- Generating Long Sequences with Sparse Transformers
- Neural Machine Translation by Jointly Learning to Align and Translate
- Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Efficient Low Rank Attention for Long-Context Inference in Large Language Models
- The Llama 3 Herd of Models
- GPT-4 Technical Report
- Efficiently Scaling Transformer Inference
- Qwen3 Technical Report
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks