IrekoGPT: Turning Structured Pruning into Post-Hoc Slimmable LLMs
cs.LG, stat.ML
Submitted: 2026-09-30
Updated: 2026-09-30
Comments: Accepted at the NeurIPS 2026 Workshop "AXIOM: Foundations of Efficient Deep Learning". 8 pages, 5 figures
Code: https://github.com/aimagelab/IrekoGPT
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
- The Llama 3 Herd of Models
- Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
- Deep Hierarchical Learning with Nested Subspace Networks for Large Language Models
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- DOTResize: Reducing LLM Width via Discrete Optimal Transport-based Neuron Merging
- Qwen3 Technical Report
- FlexRank: Nested Low-Rank Knowledge Decomposition for Adaptive Model Deployment
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