Transformers performing in-context learning implicitly implement gradient descent, ridge regression, and least-squares predictors for linear models, with behavior shifting based on model depth, width, and data noise.
Learning to prompt for vision-language models
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
Activation prompts on intermediate layers outperform input-level visual prompting and parameter-efficient fine-tuning in accuracy and efficiency across 29 datasets.
SeMoBridge projects images into the text modality via a semantic bridge to reduce CLIP's intra-modal misalignment and improve few-shot performance.
ComMem proposes complementary fast visual cache and slow textual prototype memories for test-time adaptation of VLMs, claiming superior performance on 15 benchmarks under distribution shifts.
citing papers explorer
-
What learning algorithm is in-context learning? Investigations with linear models
Transformers performing in-context learning implicitly implement gradient descent, ridge regression, and least-squares predictors for linear models, with behavior shifting based on model depth, width, and data noise.
-
Visual prompting reimagined: The power of the Activation Prompts
Activation prompts on intermediate layers outperform input-level visual prompting and parameter-efficient fine-tuning in accuracy and efficiency across 29 datasets.
-
SeMoBridge: Semantic Modality Bridge for Efficient Few-Shot Adaptation of CLIP
SeMoBridge projects images into the text modality via a semantic bridge to reduce CLIP's intra-modal misalignment and improve few-shot performance.
-
ComMem: Complementary Memory Systems for Test-Time Adaptation of Vision-Language Models
ComMem proposes complementary fast visual cache and slow textual prototype memories for test-time adaptation of VLMs, claiming superior performance on 15 benchmarks under distribution shifts.