RaPO reduces catastrophic forgetting in visual continual learning by shaping rewards around policy drift and stabilizing advantages with cross-task exponential moving averages during reinforcement fine-tuning of multimodal models.
Learning transferable visual models from natural language supervision
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
baseline 1
method 1
citation-polarity summary
fields
cs.CV 7representative citing papers
InstrAction pretrains video foundation models using action-centric data filtering, hard negatives, an Action Perceiver module, DTW-Align, and Masked Action Modeling to reduce static bias and outperform prior models on a new InstrAct Bench for semantic, procedural, and retrieval tasks.
DeepSpeak provides over 100 hours of consented, identity-matched real and modern deepfake audiovisual content focused on talking heads, with evaluations showing existing detectors fail to generalize without retraining.
LAION-5B is an openly released dataset of 5.85 billion CLIP-filtered image-text pairs that enables replication of foundational vision-language models.
Policy entropy remains constant in flow-matching models during RLHF due to fixed noise schedules while perceptual diversity collapses from mode-seeking policy gradients, so perceptual entropy constraints are introduced to preserve diversity and improve quality.
ForgeVLA enables federated VLA model training from unlabeled vision-action pairs by recovering language via embodied classifiers and using contrastive planning plus adaptive aggregation to avoid feature collapse.
ViBE generates M/EEG signals from visual stimuli by reconstructing neural responses with a TSC-VAE and aligning CLIP image features to its latent space via Q-Former, MSE, and sliced Wasserstein losses.
citing papers explorer
-
When Policy Entropy Constraint Fails: Preserving Diversity in Flow-based RLHF via Perceptual Entropy
Policy entropy remains constant in flow-matching models during RLHF due to fixed noise schedules while perceptual diversity collapses from mode-seeking policy gradients, so perceptual entropy constraints are introduced to preserve diversity and improve quality.