MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization
cs.LG, cs.AI, cs.CV
Submitted: 2026-05-18
Updated: 2026-11-07
Code: https://github.com/meta-llama/llama3
Terminology
Sources
- PID Control-Based Self-Healing to Improve the Robustness of Large Language Models
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
- Rethinking Residual Errors in Compensation-based LLM Quantization
- BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction
- GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibration
- Low-bit Model Quantization for Deep Neural Networks: A Survey
- SpinQuant: LLM quantization with learned rotations
- Pointer Sentinel Mixture Models
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization
- Qwen3 Technical Report
- I&S-ViT: An Inclusive & Stable Method for Pushing the Limit of Post-Training ViTs Quantization
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- 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