Papers by Miles Williams
Compressing Language Models for Specialized Domains (2026.eacl-long)
Copied to clipboard
| Challenge: | Language models (LMs) excel at tasks across diverse domains, yet require substantial computational resources during inference. |
| Approach: | They propose a calibration method to improve the in-domain performance of compressed LMs in a post-training setting. |
| Outcome: | The proposed method outperforms existing methods on domain-specific tasks while preserving general performance. |
On the Impact of Calibration Data in Post-training Quantization and Pruning (2024.acl-long)
Copied to clipboard
| Challenge: | Quantization and pruning are the foundations of compression for large language models . however, no prior work has investigated how calibration data impacts performance of compression methods. |
| Approach: | They propose an empirical study on the effect of calibration data on LLM performance. |
| Outcome: | The proposed methods improve performance in a post-training setting. |
Self-calibration for Language Model Quantization and Pruning (2025.naacl-long)
Copied to clipboard
| Challenge: | Quantization and pruning are fundamental approaches for model compression, but they require large computational resources. |
| Approach: | They propose to use model calibration data to generate synthetic calibrations to improve model performance. |
| Outcome: | The proposed method outperforms other methods using real data in a post-training setting. |
Speculative Decoding with a Speculative Vocabulary (2026.findings-acl)
Copied to clipboard
| Challenge: | Speculative decoding methods use a draft model to accelerate inference while yielding identical outputs. |
| Approach: | They propose a method that selects a vocabulary subset per decoding step and uses a draft model to generate a series of tokens that are verified in parallel. |
| Outcome: | The proposed method achieves higher acceptance length than state-of-the-art speculative decoding method, EAGLE-3. |