YANchor-4B: Effective Long-Horizon Reasoning in O(N) Time with O(1) Memory

arXiv:2610.10118 · cs.LG, cs.CL · Submitted 2026-10-07 · Read on arXiv

cs.LG, cs.CL

Submitted: 2026-10-07

Updated: 2026-10-07

Code: https://github.com/RocoreMatrix/YANchor

Terminology

• Benchmark — 33× in this paper · explained in 2 episodes
• Accuracy — 26× in this paper · explained in 1 episode
• Decode — 14× in this paper · explained in 2 episodes
• Transformer — 9× in this paper · explained in 2 episodes
• Adaptation — 7× in this paper · explained in 1 episode
• Hybrid Models — 2× in this paper · explained in 2 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Allocator — 1× in this paper · explained in 1 episode
• Distillation — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• F1 Score — 1× in this paper · explained in 3 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• KV cache — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Verifiable Rewards — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes
• Vision-language models — 1× in this paper · explained in 2 episodes

Sources

• Gated Delta Networks: Improving Mamba2 with Delta Rule
• Mamba: Linear-Time Sequence Modeling with Selective State Spaces
• RecurrentGemma: Moving Past Transformers for Efficient Open Language Models
• xLSTM: Extended Long Short-Term Memory
• Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling
• RWKV-7 "Goose" with Expressive Dynamic State Evolution
• RADLADS: Rapid Attention Distillation to Linear Attention Decoders at Scale
• Artificial Hippocampus Networks for Efficient Long-Context Modeling
• xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference
• Scaling Reasoning without Attention
• On Subquadratic Architectures: From Applications to Principles
• Super Apriel: One Checkpoint, Many Speeds
• A Hippocampus for Linear Attention: An Exact Memory for What the Recurrent State Forgets
• Training Verifiers to Solve Math Word Problems
• Let's Verify Step by Step
• Measuring Massive Multitask Language Understanding
• MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark
• Are We Done with MMLU?
• CMMLU: Measuring massive multitask language understanding in Chinese
• C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models

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