arXiv:2606. 06892v1 Announce Type: new Abstract: Scalable data attribution methods typically assign isolated utility scores to individual training examples.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.
arXiv:2603. 09493v2 Announce Type: replace-cross Abstract: The adaptation of large-scale vision-language models (VLMs) to downstream tasks with limited labeled data remains a significant challenge.
arXiv:2606. 12109v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have demonstrated remarkable zero-shot generalization in robotic manipulation, yet the vast majority of pre-trained pipelines remain strictly confined to low-DoF parallel grippers.
arXiv:2607. 09450v1 Announce Type: cross Abstract: Pre-trained Vision-Language Models (VLMs) such as CLIP achieve strong zero-shot generalization, but their performance degrades sharply under adversarial perturbations.
arXiv:2606. 01710v1 Announce Type: cross Abstract: Vision-Language models (VLMs), such as CLIP, achieve powerful zero-shot classification.
The paper introduces EvoPrompt, a framework for adapting vision‑language models to new tasks with limited data while preventing catastrophic forgetting. EvoPrompt uses a Modality‑Shared Prompt Projector to create hierarchical prompts and an evolutionary training strategy that separates low‑rank updates into directional and magnitude components, preserving learned semantic directions. Experiments show that EvoPrompt achieves state‑of‑the‑art few‑shot performance while maintaining the original zero‑shot capabilities of the pre‑trained models.
FedBST introduces a bilateral self‑training framework for unsupervised federated classification using Vision‑Language Models. It addresses the shortcomings of prior methods by exploiting both high‑confidence and ambiguous samples through uncertainty‑aware confidence penalization (UACP) during local training and a visual‑text ensemble strategy at inference. Experiments show that FedBST consistently outperforms existing approaches under standard federated aggregation protocols.