| | Dominance in AI will come from achieving interpretability [pdf] (baulab.info) |
|
1 point by delichon 52 days ago | past
|
|
| | Auditing AI Bias: The DeepSeek Case (baulab.info) |
|
4 points by thamer 76 days ago | past | 1 comment
|
|
| | Linearity of Relation Decoding in Transformer Language Models (baulab.info) |
|
1 point by yeesian on March 30, 2024 | past
|
|
| | Concept sliders: LoRA adaptors for precise control in diffusion models (baulab.info) |
|
153 points by billconan on Dec 12, 2023 | past | 57 comments
|
|
| | Function Vectors in Large Language Models (baulab.info) |
|
1 point by jdkee on Oct 26, 2023 | past
|
|
| | Mass editing memory in a transformer (baulab.info) |
|
142 points by rodoxcasta on April 21, 2023 | past | 51 comments
|
|
| | Locating and Editing Factual Associations in GPT (baulab.info) |
|
1 point by raidicy on April 10, 2023 | past
|
|
| | Erasing Concepts from Diffusion Models (baulab.info) |
|
1 point by PinkRidingHood on March 29, 2023 | past
|
|
| | Locating and Editing Factual Associations in GPT (baulab.info) |
|
1 point by codeulike on March 3, 2023 | past | 1 comment
|
|
| | Locating and Editing Factual Associations in GPT (baulab.info) |
|
1 point by kvee on Dec 20, 2022 | past
|
|
| | Locating and Editing Factual Associations in GPT (baulab.info) |
|
12 points by bilsbie on July 11, 2022 | past
|
|
