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.
Available: http://arxiv.org/abs/2002.07017
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
MOSAIC learns overlap-aware shared-specific representations, fits a first-stage predictor on overlapping data, and calibrates the gap using target-pattern samples, with non-asymptotic error bounds decomposing overlap size, calibration gap, and representation error.
DMIL is a multimodal learning framework that decomposes sample-specific interactions into redundant, unique, and synergistic components via variational architecture and uses them for adaptive fine-tuning.
Surrounding agents frequently degrade trajectory prediction accuracy in interactive driving scenes, and integrating a Conditional Information Bottleneck improves results by ignoring non-beneficial contextual signals.
CmIR uses causal inference to separate invariant causal representations from spurious ones in multimodal data, improving generalization under distribution shifts and noise via invariance, mutual information, and reconstruction constraints.
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.
-
Pattern-Calibrated Multimodal Prediction under Blockwise Missingness
MOSAIC learns overlap-aware shared-specific representations, fits a first-stage predictor on overlapping data, and calibrates the gap using target-pattern samples, with non-asymptotic error bounds decomposing overlap size, calibration gap, and representation error.
-
Information-Theoretic Decomposition for Multimodal Interaction Learning
DMIL is a multimodal learning framework that decomposes sample-specific interactions into redundant, unique, and synergistic components via variational architecture and uses them for adaptive fine-tuning.
-
Super Agents and Confounders: Influence of surrounding agents on vehicle trajectory prediction
Surrounding agents frequently degrade trajectory prediction accuracy in interactive driving scenes, and integrating a Conditional Information Bottleneck improves results by ignoring non-beneficial contextual signals.
-
Learning Invariant Modality Representation for Robust Multimodal Learning from a Causal Inference Perspective
CmIR uses causal inference to separate invariant causal representations from spurious ones in multimodal data, improving generalization under distribution shifts and noise via invariance, mutual information, and reconstruction constraints.