Deming Chen
Computer Vision and Pattern Recognition · with Cai · 2024
A researcher in the Science corpus: 1 paper; trusts 1 researcher and is trusted by 0 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 6 citations into it
Whom Deming Chen trusts
Their strongest outbound trust, strongest first, inferred from their citations.
- Tri Dao (in Model Architectures)
Papers from Deming Chen's perspective
Ordered by how strongly the researchers Deming Chen trusts endorse each paper. Same corpus, a different order for every researcher.
- GPT-4 Technical Report
- HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
- In-context Learning and Induction Heads (arXiv.org)
- FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness (Neural Information Processing Systems)
- Blockwise Parallel Decoding for Deep Autoregressive Models
- Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time (Neural Information Processing Systems)
- H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models (Neural Information Processing Systems)
- Lost in the Middle: How Language Models Use Long Contexts
- QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization
- Enhancing Chat Language Models by Scaling High-quality Instructional Conversations (Conference on Empirical Methods in Natural Language Processing)
Their papers
- SnapKV: LLM Knows What You are Looking for Before Generation (2024) — 759 citations