PairAlign learns compact variable-length token sequences for audio via self-alignment on paired content-preserving views, achieving 55% fewer archive tokens than VQ while preserving edit-distance retrieval at 12.71 tokens/s.
A-jepa: Joint-embedding predictive architecture can listen
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 9roles
background 2polarities
background 2representative citing papers
RVM uses recurrent computation inside a masked autoencoder to learn video representations that match or exceed prior video and image models on classification, tracking, and dense spatial tasks with up to 30x better parameter efficiency.
PupuJEPA applies a visual JEPA framework to 2D spectrograms with music-specific adaptations and outperforms 1D SSL models on the MARBLE benchmark for multiple MIR tasks.
MJ EPA applies a single shared ViT encoder and one predictive objective within and across audio-visual modalities, reporting >6.8 mAP gains on AudioSet-20K and competitive video results with 10x less data.
AudioMosaic learns general-purpose audio representations through contrastive pre-training with structured spectrogram masking, reaching state-of-the-art results on standard benchmarks and improving audio-language tasks.
AeroJEPA applies joint-embedding predictive learning to produce scalable, semantically organized latent representations for 3D aerodynamic fields that support both field reconstruction and downstream design tasks.
AGE applies adaptive masking via a learnable sampler in Transformer-based SSL to align graph and text embeddings, yielding higher accuracy on four GraphQA benchmarks for non-parametric GraphRAG.
ST-STORM introduces a dual-branch SSL framework that disentangles semantic content from stylistic appearance using gated latent streams, JEPA for content invariance, and adversarial constraints for style capture.
A survey that clarifies boundaries and organizes World Action Models by generation requirements and predictive substrates, identifying a trend toward generating less of the future.
citing papers explorer
-
PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization
PairAlign learns compact variable-length token sequences for audio via self-alignment on paired content-preserving views, achieving 55% fewer archive tokens than VQ while preserving edit-distance retrieval at 12.71 tokens/s.
-
Recurrent Video Masked Autoencoders
RVM uses recurrent computation inside a masked autoencoder to learn video representations that match or exceed prior video and image models on classification, tracking, and dense spatial tasks with up to 30x better parameter efficiency.
-
Frequency-Aware Self-Supervised Music Representation Learning
PupuJEPA applies a visual JEPA framework to 2D spectrograms with music-specific adaptations and outperforms 1D SSL models on the MARBLE benchmark for multiple MIR tasks.
-
MJEPA: A Simple and Scalable Joint-Embedding Predictive Architecture for Audio-Visual Learning
MJ EPA applies a single shared ViT encoder and one predictive objective within and across audio-visual modalities, reporting >6.8 mAP gains on AudioSet-20K and competitive video results with 10x less data.
-
AudioMosaic: Contrastive Masked Audio Representation Learning
AudioMosaic learns general-purpose audio representations through contrastive pre-training with structured spectrogram masking, reaching state-of-the-art results on standard benchmarks and improving audio-language tasks.
-
AeroJEPA: Learning Semantic Latent Representations for Scalable 3D Aerodynamic Field Modeling
AeroJEPA applies joint-embedding predictive learning to produce scalable, semantically organized latent representations for 3D aerodynamic fields that support both field reconstruction and downstream design tasks.
-
AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation
AGE applies adaptive masking via a learnable sampler in Transformer-based SSL to align graph and text embeddings, yielding higher accuracy on four GraphQA benchmarks for non-parametric GraphRAG.
-
Stylistic-STORM (ST-STORM) : Perceiving the Semantic Nature of Appearance
ST-STORM introduces a dual-branch SSL framework that disentangles semantic content from stylistic appearance using gated latent streams, JEPA for content invariance, and adversarial constraints for style capture.
-
World Action Models: A Survey
A survey that clarifies boundaries and organizes World Action Models by generation requirements and predictive substrates, identifying a trend toward generating less of the future.