Ngai Wong
11 papers · 7 citations
Most-cited papers
- Scaling Laws With Vocabulary: Larger Models Deserve Larger Vocabularies2024 · 112 citations
- APTQ: Attention-aware Post-training Mixed-precision Quantization For Large Language Models2024 · 39 citations
- Loretta: Low-rank Economic Tensor-train Adaptation For Ultra-low-parameter Fine-tuning Of Large Language Models2024 · 19 citations
- Uncomp: Can Matrix Entropy Uncover Sparsity? -- A Compressor Design From An Uncertainty-aware Perspective2024 · 14 citations
Topics