Misreading Chat

146 Episodes

1. #143 – SWE-bench: Can Language Models Resolve Real-World GitHub Issues?

   Published: 12/11/2024
2. #142: An Empirical Study of Rust-for-Linux: The Success, Dissatisfaction, and Compromise

   Published: 12/4/2024
3. #141: SQL Has Problems. We Can Fix Them: Pipe Syntax In SQL

   Published: 11/13/2024
4. #140: GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models

   Published: 10/24/2024
5. #139: NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis

   Published: 10/2/2024
6. #138: Distilling the Knowledge in a Neural Network

   Published: 9/11/2024
7. #137: Optimal Quantile Approximation in Streams

   Published: 8/13/2024
8. #136: Distinct Elements in Streams: An Algorithm for the (Text) Book

   Published: 8/7/2024
9. #135: In-Datacenter Performance Analysis of a Tensor Processing Unit

   Published: 7/2/2024
10. #134: LoRA: Low-Rank Adaptation of Large Language Models

    Published: 6/9/2024
11. #133: Triton: An Intermediate Language and Compiler for Tiled Neural Network Computations

    Published: 5/21/2024
12. #132: High-Resolution Image Synthesis with Latent Diffusion Models

    Published: 5/2/2024
13. #131: FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness

    Published: 4/23/2024
14. #130: Diffusion models from scratch, from a new theoretical perspective

    Published: 4/5/2024
15. #129: Programming Massively Parallel Processors (Ch.4- Ch.6)

    Published: 3/26/2024
16. #128: Faiss: A library for efficient similarity search and clustering of dense vectors.

    Published: 3/9/2024
17. #127: Programming Massively Parallel Processors (Ch.1- Ch.3)

    Published: 2/29/2024
18. #126: Vector Database Management Systems

    Published: 1/30/2024
19. #125: Always-on Vision Processing Unit for Mobile Applications

    Published: 1/23/2024
20. #124: GAIA: a benchmark for General AI Assistants

    Published: 12/22/2023