Towards Training-free Automatic Proxy Discovery via Large Language Models for Mixed Precision Quantization
cs.LG, cs.CV
Submitted: 2025-12-08
Updated: 2026-09-20
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- PACT: Parameterized Clipping Activation for Quantized Neural Networks
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Qwen3 Technical Report
- Mixed-Precision Quantized Neural Network with Progressively Decreasing Bitwidth For Image Classification and Object Detection
- Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search
- Where and How to Enhance: Discovering Bit-Width Contribution for Mixed Precision Quantization
- Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning
- BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction
- FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer
- MPTQ-ViT: Mixed-Precision Post-Training Quantization for Vision Transformer
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