Latest Exact Match Attention
cs.LG, cs.CC, cs.CL
Submitted: 2026-09-22
Updated: 2026-09-22
Code: https://github.com/moritzbroe/latest_exact_match_attention
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- The Markovian Thinker: Architecture-Agnostic Linear Scaling of Reasoning
- Zoology: Measuring and Improving Recall in Efficient Language Models
- Titans: Learning to Memorize at Test Time
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- Memory Layers at Scale
- The Expressive Power of Low Precision Softmax Transformers with (Summarized) Chain-of-Thought
- Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity
- Extending Context Window of Large Language Models via Positional Interpolation
- Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
- Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
- A Hippocampus for Linear Attention: An Exact Memory for What the Recurrent State Forgets
- DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
- DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
- Learning Transformer Programs
- Log-Linear Attention
- Training Compute-Optimal Large Language Models
- Hamming Attention Distillation: Binarizing Keys and Queries for Efficient Long-Context Transformers
- RULER: What's the Real Context Size of Your Long-Context Language Models?
- Kimi Linear: An Expressive, Efficient Attention Architecture
- Neural Random-Access Machines
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