DecQ uses detail-condensing queries on shallow and deep VFM features to improve both reconstruction PSNR and generative convergence/FID in RAEs without fine-tuning the encoder.
Neural discrete representation learning
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
R3-VAE stabilizes semantic identifier generation for generative recommendation via reference vector guidance and rating residual quantization, delivering 14.5% average Recall@10 and 15.5% NDCG@10 gains on public datasets plus 1.62% MRR improvement in online A/B tests.
PRiSE-EEG is a prior-guided EEG foundation model that allocates shared and specialized experts across depth using CKA-derived sigmoid mappings and reports strong cross-paradigm results on 12 benchmarks.
Self Forcing trains autoregressive video diffusion models by performing autoregressive rollout with KV caching during training to close the exposure bias gap, using a holistic video-level loss and few-step diffusion for efficiency.
citing papers explorer
-
DecQ: Detail-Condensing Queries for Enhanced Reconstruction and Generation in Representation Autoencoders
DecQ uses detail-condensing queries on shallow and deep VFM features to improve both reconstruction PSNR and generative convergence/FID in RAEs without fine-tuning the encoder.
-
R3-VAE: Reference Vector-Guided Rating Residual Quantization VAE for Generative Recommendation
R3-VAE stabilizes semantic identifier generation for generative recommendation via reference vector guidance and rating residual quantization, delivering 14.5% average Recall@10 and 15.5% NDCG@10 gains on public datasets plus 1.62% MRR improvement in online A/B tests.
-
PRiSE-EEG: A Prior-Guided Foundation Model with Depth-Stratified Experts for Cross-Paradigm EEG Representation Learning
PRiSE-EEG is a prior-guided EEG foundation model that allocates shared and specialized experts across depth using CKA-derived sigmoid mappings and reports strong cross-paradigm results on 12 benchmarks.
-
Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion
Self Forcing trains autoregressive video diffusion models by performing autoregressive rollout with KV caching during training to close the exposure bias gap, using a holistic video-level loss and few-step diffusion for efficiency.