Qingyao Sun
Efficiency & Compression · 2024
A researcher in the Science corpus: 1 paper; trusts 3 researchers and is trusted by 0 researchers here, as inferred from the citation graph.
Subfields
- Efficiency & Compression — 5 citations into it
Whom Qingyao Sun trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
Papers from Qingyao Sun's perspective
Ordered by how strongly the researchers Qingyao Sun trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Llama 2: Open Foundation and Fine-Tuned Chat Models (arXiv.org)
- Attention is All you Need (Neural Information Processing Systems)
- Up or Down? Adaptive Rounding for Post-Training Quantization
- ImageNet classification with deep convolutional neural networks
- QuIP: 2-Bit Quantization of Large Language Models With Guarantees (Neural Information Processing Systems)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- The case for 4-bit precision: k-bit Inference Scaling Laws
- FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness (Neural Information Processing Systems)
- Long Short-Term Memory
Their papers
- QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks (2024) — 366 citations