Preserving Updates in Low-Bit Recurrent State Quantization

arXiv:2610.15709 · cs.LG, cs.CL · Submitted 2026-10-11 · Read on arXiv

cs.LG, cs.CL

Submitted: 2026-10-11

Updated: 2026-10-11

Terminology

• Quantization — 1× in this paper · explained in 12 episodes

Sources

• Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes
• Just read twice: closing the recall gap for recurrent language models
• Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
• GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
• Decoupled Weight Decay Regularization
• Pointer Sentinel Mixture Models
• Mixed Precision Training
• A White Paper on Neural Network Quantization
• Retentive Network: A Successor to Transformer for Large Language Models
• Revisiting BFloat16 Training
• DAMP: Decay-Aware Mixed-Precision Recurrent-State Quantization

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: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks