Next-acceleration-scale autoregressive prediction in discrete latent space with on-policy privileged information distillation yields improved MRI reconstructions from sparse measurements on the fastMRI benchmark.
Advances in neural information processing systems30(2017)
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6representative citing papers
A hierarchical spatiotemporal vector quantization framework segments skeleton-based actions without supervision, achieving new state-of-the-art results on HuGaDB, LARa, and BABEL while reducing segment length bias.
Ego3DLM jointly predicts past and future 3D body pose and motion descriptions in a single autoregressive pass, conditioned on egocentric video, 3D scene features, and three-point tracking, achieving state-of-the-art on the Nymeria benchmark.
Band-wise independent VQ-VAE tokenizers per EEG frequency band plus masked Transformer pretraining on 9,200+ subjects yields top reported transfer on three cognitive tasks.
MEPA adds token-routed MoE and residual self-supervised feature alignment to VAR models, reporting better FID on ImageNet 256x256 with half the training epochs and fewer parameters than dense baselines.
VQSOP applies sparsity-exploiting vector quantization and a dual-branch refinement module to cut communication volume by up to 82x while claiming state-of-the-art 3D occupancy prediction performance.
citing papers explorer
-
Next-Acceleration-Scale Prediction for Autoregressive MRI Reconstruction
Next-acceleration-scale autoregressive prediction in discrete latent space with on-policy privileged information distillation yields improved MRI reconstructions from sparse measurements on the fastMRI benchmark.
-
Unsupervised Skeleton-Based Action Segmentation via Hierarchical Spatiotemporal Vector Quantization
A hierarchical spatiotemporal vector quantization framework segments skeleton-based actions without supervision, achieving new state-of-the-art results on HuGaDB, LARa, and BABEL while reducing segment length bias.
-
Ego-Human Motion Prediction with 3D-Aware LLM
Ego3DLM jointly predicts past and future 3D body pose and motion descriptions in a single autoregressive pass, conditioned on egocentric video, 3D scene features, and three-point tracking, achieving state-of-the-art on the Nymeria benchmark.
-
BandVQ: Band-Wise Vector-Quantized EEG Foundation Model
Band-wise independent VQ-VAE tokenizers per EEG frequency band plus masked Transformer pretraining on 9,200+ subjects yields top reported transfer on three cognitive tasks.
-
MEPA: Multi-Scale Representation Alignment for Visual Autoregressive Modeling with Mixture of Experts
MEPA adds token-routed MoE and residual self-supervised feature alignment to VAR models, reporting better FID on ImageNet 256x256 with half the training epochs and fewer parameters than dense baselines.
-
Sparse-Aware Vector Quantization for Bandwidth-Efficient Collaborative 3D Semantic Occupancy Prediction
VQSOP applies sparsity-exploiting vector quantization and a dual-branch refinement module to cut communication volume by up to 82x while claiming state-of-the-art 3D occupancy prediction performance.