REVIEW 5 cited by
Latent Space Translation via Inverse Relative Projection
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The emergence of similar representations between independently trained neural models has sparked significant interest in the representation learning community, leading to the development of various methods to obtain communication between latent spaces. "Latent space communication" can be achieved in two ways: i) by independently mapping the original spaces to a shared or relative one; ii) by directly estimating a transformation from a source latent space to a target one. In this work, we combine the two into a novel method to obtain latent space translation through the relative space. By formalizing the invertibility of angle-preserving relative representations and assuming the scale invariance of decoder modules in neural models, we can effectively use the relative space as an intermediary, independently projecting onto and from other semantically similar spaces. Extensive experiments over various architectures and datasets validate our scale invariance assumption and demonstrate the high accuracy of our method in latent space translation. We also apply our method to zero-shot stitching between arbitrary pre-trained text and image encoders and their classifiers, even across modalities. Our method has significant potential for facilitating the reuse of models in a practical manner via compositionality.
Forward citations
Cited by 5 Pith papers
-
A Stitch in Time Saves Nine: Preserving Policy Compatibility Under Perception Updates in End-to-End Autonomous Driving
Lightweight model stitching preserves over 91% of driving performance in cross-domain perception updates for end-to-end autonomous driving, cutting adaptation time from 22 hours to under 1 hour.
-
$\boldsymbol{\lambda}$-Orthogonality Regularization for Compatible Representation Learning
λ-Orthogonality regularization enables distribution-specific adaptation of representations via affine transformations while retaining original learned structures.
-
Latent Space Alignment for AI-Native MIMO Semantic Communications
Joint MIMO precoder/decoder optimization for latent space alignment outperforms disjoint semantic alignment and channel equalization in simulations.
-
Improving Relative Representations with Learned Anchors and Whitened Inner Products
Learned anchors as semantic prototypes combined with whitened inner products improve relative representations, enabling nearly lossless zero-shot communication between heterogeneous neural models on vision and language tasks.
-
Frame-Based Zero-Shot Semantic Channel Equalization for AI-Native Communications
Using Parseval-frame projections onto shared anchor features, a receiver can approximately reconstruct the latent vectors of an unseen, independently trained encoder; a Lyapunov scheduler then allocates bandwidth, CPU...
Discussion (0). Sign in to comment.