CORP: Closed-Form One-shot Representation-Preserving Structured Pruning
cs.LG, cs.CV
Submitted: 2026-02-05
Updated: 2026-11-09
Terminology
Sources
- QLoRA: Efficient Finetuning of Quantized LLMs
- SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot
- GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
- Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning
- The Need for Speed: Pruning Transformers with One Recipe
- AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
- Preserving Deep Representations In One-Shot Pruning: A Hessian-Free Second-Order Optimization Framework
- Pointer Sentinel Mixture Models
- Gradient-Free Structured Pruning with Unlabeled Data
- DINOv2: Learning Robust Visual Features without Supervision
- Vote&Mix: Plug-and-Play Token Reduction for Efficient Vision Transformer
- ImageNet Large Scale Visual Recognition Challenge
- WoodFisher: Efficient Second-Order Approximation for Neural Network Compression
- A Simple and Effective Pruning Approach for Large Language Models
- GRAIL: Post-hoc Compensation by Linear Reconstruction for Compressed Networks
- DeiT III: Revenge of the ViT
- Zero-TPrune: Zero-Shot Token Pruning through Leveraging of the Attention Graph in Pre-Trained Transformers
- SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
- OPT: Open Pre-trained Transformer Language Models
- Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs
Related papers
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis
- (Mis)generalization of Helpful-Only Fine-tuning