Post-Boundary Bridge: Must Local Attention Go Global Between Global Layers?
cs.LG
Submitted: 2026-06-01
Updated: 2026-09-17
Comments: 36 pages, 9 figures
Code: https://github.com/gkamradt/LLMTest_NeedleInAHaystack
Project page: https://skylion007.github.io/OpenWebTextCorpus
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Longformer: The Long-Document Transformer
- Generating Long Sequences with Sparse Transformers
- LongNet: Scaling Transformers to 1,000,000,000 Tokens
- AbsenceBench: Language Models Can't Tell What's Missing
- Gemma 2: Improving Open Language Models at a Practical Size
- RULER: What's the Real Context Size of Your Long-Context Language Models?
- Mistral 7B
- Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention
- Qwen2.5 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