DictLLM: Post-training Compression of Large Language Model with Dictionary Kernels
cs.AI, cs.LG
Submitted: 2026-11-05
Updated: 2026-11-05
Code: https://github.com/IST-DASLab/qutlass
Terminology
Sources
- ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models
- Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
- CoSpaDi: Compressing LLMs via Calibration-Guided Sparse Dictionary Learning
- LLaMA: Open and Efficient Foundation Language Models
- OPT: Open Pre-trained Transformer Language Models
- Mistral 7B
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Qwen3 Technical Report
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents