Elastic Selective Spectral Hybrids for Train-Once, Export-Many Budgeted Inference
cs.LG
Submitted: 2026-09-26
Updated: 2026-09-26
Terminology
Sources
- Spectral State Space Models
- Just read twice: closing the recall gap for recurrent language models
- Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes
- Longformer: The Long-Document Transformer
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Zamba: A Compact 7B SSM Hybrid Model
- The Llama 3 Herd of Models
- Distilling the Knowledge in a Neural Network
- Mistral 7B
- Matryoshka Representation Learning
- Flash STU: Fast Spectral Transform Units
- Pointer Sentinel Mixture Models
- Compressive Transformers for Long-Range Sequence Modelling
- GLU Variants Improve Transformer
- MatMamba: A Matryoshka State Space Model
- Elastic Spectral State Space Models for Train-Once Budgeted Inference
- Nemotron Elastic: Towards Efficient Many-in-One Reasoning LLMs
- Training Matryoshka Mixture-of-Experts for Elastic Inference-Time Expert Utilization
- Slimmable Neural Networks
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