GDN Tree-Scan: Served Tree Verification for Recurrent-Hybrid Language Models

arXiv:2609.23900 · cs.LG · Submitted 2026-09-20 · Read on arXiv

cs.LG

Submitted: 2026-09-20

Updated: 2026-09-20

Comments: 9 pages

Code: https://github.com/MaCoredroid/Lumo

Project page: https://sglproject.github.io/advanced

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Decode — 68× in this paper · explained in 2 episodes
• Verifier — 35× in this paper · explained in 2 episodes
• Verification — 19× in this paper · explained in 2 episodes
• Speculative Decoding — 15× in this paper · explained in 2 episodes
• Trace — 6× in this paper · explained in 2 episodes
• Hybrid Models — 4× in this paper · explained in 2 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Alignment — 2× in this paper · explained in 1 episode
• Core — 2× in this paper · explained in 2 episodes
• Adaptive Draft Tree Structure — 1× in this paper · explained in 1 episode
• Hybrid Architectures — 1× in this paper · explained in 3 episodes
• KV cache — 1× in this paper · explained in 3 episodes
• Positional Bias — 1× in this paper · explained in 2 episodes
• Topological Order — 1× in this paper · explained in 2 episodes

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