| | Coding Self-Attention, Multi-Head Attention, Cross-Attention, Causal-Attention (sebastianraschka.com) |
| 142 points by rasbt on Jan 14, 2024 | past | 11 comments |
|
| | Ten Noteworthy AI Research Papers of 2023 (sebastianraschka.com) |
| 128 points by danboarder on Jan 6, 2024 | past | 19 comments |
|
| | Noteworthy AI Research Papers of 2023 (sebastianraschka.com) |
| 3 points by rasbt on Jan 1, 2024 | past |
|
| | Ten Noteworthy AI Research Papers of 2023 (sebastianraschka.com) |
| 9 points by lucasus on Dec 30, 2023 | past |
|
| | Research Papers in November 2023 (sebastianraschka.com) |
| 1 point by Anon84 on Dec 10, 2023 | past |
|
| | AI Research Papers in November 2023: hallucinations and reasoning capabilities (sebastianraschka.com) |
| 5 points by rasbt on Dec 9, 2023 | past |
|
| | Practical Tips for Finetuning LLMs Using LoRA (Low-Rank Adaptation) (sebastianraschka.com) |
| 342 points by rasbt on Nov 19, 2023 | past | 27 comments |
|
| | Why would a famous former university ML professor make his posts paywalled? (sebastianraschka.com) |
| 7 points by behnamoh on Nov 6, 2023 | past | 1 comment |
|
| | AI and Open Source in 2023 (sebastianraschka.com) |
| 123 points by belter on Nov 4, 2023 | past | 67 comments |
|
| | AI Research Papers (October 2023) (sebastianraschka.com) |
| 5 points by rasbt on Nov 4, 2023 | past |
|
| | AI and Open Source in 2023: A Review of the Year's Highs and Lows (sebastianraschka.com) |
| 2 points by rasbt on Oct 23, 2023 | past |
|
| | AI chips, acquisitions, new "small" open-source LLMs, and new LoRA techniques (sebastianraschka.com) |
| 5 points by rasbt on Oct 9, 2023 | past |
|
| | AI news editorial from custom AI chips to new "small" LLMs like phi and Mistral (sebastianraschka.com) |
| 1 point by rasbt on Oct 8, 2023 | past |
|
| | AI research papers summaries and highlights (Aug to Sep) (sebastianraschka.com) |
| 3 points by rasbt on Sept 24, 2023 | past |
|
| | Optimizing LLMs from a Dataset Perspective (sebastianraschka.com) |
| 138 points by alexmolas on Sept 15, 2023 | past | 24 comments |
|
| | PyTorch: Cross-Entropy vs. Negative Log Likelihood (sebastianraschka.com) |
| 2 points by auraham on Sept 12, 2023 | past |
|
| | Training and aligning LLMs with RLHF and RLHF alternatives (sebastianraschka.com) |
| 102 points by rasbt on Sept 10, 2023 | past | 14 comments |
|
| | Understanding Llama 2 and the New Code Llama LLMs (sebastianraschka.com) |
| 170 points by rasbt on Aug 30, 2023 | past | 34 comments |
|
| | Llama 2, CodeLlama, and GPT-4 performance: recent LLM developments and research (sebastianraschka.com) |
| 1 point by rasbt on Aug 27, 2023 | past |
|
| | AI Research Highlights in 3 Sentences or Less (July-August 2023) (sebastianraschka.com) |
| 1 point by rasbt on Aug 12, 2023 | past |
|
| | Does it beat LLMs? NN+Gzip method reimplemented and explained step-by-step (sebastianraschka.com) |
| 3 points by rasbt on July 30, 2023 | past |
|
| | State of Computer Vision 2023 (sebastianraschka.com) |
| 1 point by eugenOrl on July 24, 2023 | past |
|
| | AI and DL paper highlights June-July 2023 (sebastianraschka.com) |
| 1 point by rasbt on July 15, 2023 | past |
|
| | State of Computer Vision 2023 (sebastianraschka.com) |
| 2 points by rasbt on July 6, 2023 | past |
|
| | Accelerating PyTorch Model Training 10x (With Mixed-Precision and FSDP) (sebastianraschka.com) |
| 2 points by rasbt on June 26, 2023 | past |
|
| | Understanding Encoder and Decoder LLMs (sebastianraschka.com) |
| 5 points by rasbt on June 17, 2023 | past |
|
| | AI Research Highlights in 3 Sentences or Less (May-June 2023) (sebastianraschka.com) |
| 2 points by rasbt on June 10, 2023 | past |
|
| | Recapping recent LLM research concerning tuning strategies and data efficiency (sebastianraschka.com) |
| 2 points by rasbt on June 3, 2023 | past |
|
| | Finetuning LLMs Efficiently with Adapters (sebastianraschka.com) |
| 1 point by Anon84 on May 27, 2023 | past |
|
| | Why the original transformer figure is wrong, and some other tidbits about LLMs (sebastianraschka.com) |
| 237 points by rasbt on May 24, 2023 | past | 49 comments |
|
|
| More |
