Bharat Venkitesh

Computer Vision and Pattern Recognition · 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 Bharat Venkitesh trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Tri Dao

Papers from Bharat Venkitesh's perspective

Ordered by how strongly the researchers Bharat Venkitesh trusts endorse each paper. Same corpus, a different order for every researcher.

1. GPT-4 Technical Report
2. HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
3. In-context Learning and Induction Heads (arXiv.org)
4. FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness (Neural Information Processing Systems)
5. Blockwise Parallel Decoding for Deep Autoregressive Models
6. Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time (Neural Information Processing Systems)
7. H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models (Neural Information Processing Systems)
8. Lost in the Middle: How Language Models Use Long Contexts
9. QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization
10. FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

Their papers

• SnapKV: LLM Knows What You are Looking for Before Generation (2024) — 759 citations