Skip to main content
Search

# Centered Kernel Alignment (CKA)

3 related articles

Subscribe to updates
  1. arXiv

    Molecule-language models get a structure lesson: SAGA trains only, lifting retrieval R@1 by up to 7.82 points

    Molecule-language models learn from paired structure-text contrastive objectives, yet they treat a structurally related nonmatch and an unrelated molecule as the same negative class. SAGA uses Centered Kernel Alignment during training to align pairwise relationships among neural molecular embeddings with fingerprint Tanimoto similarity, adding no parameters and requiring no fingerprints at inference. On MolCA and Atomas, every reported molecule-text retrieval metric improves, with Atomas-L text-to-molecule R@1 rising from 43.15 to 50.97, and non-exact retrieval shifts toward closer structural analogues.

  2. arXiv

    Speculative decoding stops picking layers by position: entropy and CKA choose the set, lifting accepted tokens by about 0.085 on Qwen3

    Which target-model hidden layers a speculative-decoding draft model should see can now be chosen by information content and redundancy instead of a fixed positional rule; on Qwen3-4B-Instruct the selected three-layer set averages about 0.085 more accepted tokens than the EAGLE3 default.

  3. arXiv

    Three-objective fusion and a multi-branch architecture let a wireless foundation model beat single-objective encoders on six downstream tasks with about one-third of their parameters

    The work proposes a fusion framework combining representations from three self-supervised objectives, MAE, JEPA, and SimCLR, and a multi-branch architecture with a shared trunk and objective-specific branches; after pretraining on roughly 25,000 spectrogram and CSI samples, at equal output embedding dimension fusion outperforms the evaluated single-objective encoders on all six downstream tasks spanning communication, sensing, and positioning while using about one-third of their parameters, and the multi-branch architecture retains much of the fusion benefit within a single-encoder parameter budget, with representation analyses indicating complementary contributions across objectives and much of the added benefit retained in components orthogonal to MAE's representation subspace.

You’re all caught up