SLAD uses shared LoRA adapters in joint training to align teacher-student features, boosting both models' performance and halving training time versus fine-tuning in distillation.
Adaptformer: Adapting vision transformers for scalable visual recog- nition
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
Hystar adapts CLIP-like models to unseen query styles by generating per-input singular-value perturbations with a hypernetwork for attention layers and a new StyleNCE contrastive loss.
SinglePrompt achieves state-of-the-art results in task-free online continual learning by replacing prompt selection with a single prompt per attention block, cosine-based classifier logits, and masking unexposed classes.
BlackVIP adapts foundation models via a Coordinator for input-dependent visual prompts and SPSA-GC for gradient estimation, enabling robust transfer on 19 datasets with low memory use and a link to randomized smoothing robustness.
A training recipe combining domain-adaptive fine-tuning, multi-source mixing, balanced sampling, and synthetic augmentations on SegMAN-S achieves 59.9% mIoU on the adverse weather test set with a 6.5-point validation-test gap.
citing papers explorer
-
SLAD : Shared LoRA Adapters for Task Specific Distillation
SLAD uses shared LoRA adapters in joint training to align teacher-student features, boosting both models' performance and halving training time versus fine-tuning in distillation.
-
Hystar: Hypernetwork-driven Style-adaptive Retrieval via Dynamic SVD Modulation
Hystar adapts CLIP-like models to unseen query styles by generating per-input singular-value perturbations with a hypernetwork for attention layers and a new StyleNCE contrastive loss.
-
Is Prompt Selection Necessary for Task-Free Online Continual Learning?
SinglePrompt achieves state-of-the-art results in task-free online continual learning by replacing prompt selection with a single prompt per attention block, cosine-based classifier logits, and masking unexposed classes.
-
Robust Adaptation of Foundation Models with Black-Box Visual Prompting
BlackVIP adapts foundation models via a Coordinator for input-dependent visual prompts and SPSA-GC for gradient estimation, enabling robust transfer on 19 datasets with low memory use and a link to randomized smoothing robustness.
-
Bridging the Generalization Gap in Adverse Weather Segmentation: A Training Recipe Perspective
A training recipe combining domain-adaptive fine-tuning, multi-source mixing, balanced sampling, and synthetic augmentations on SegMAN-S achieves 59.9% mIoU on the adverse weather test set with a 6.5-point validation-test gap.