method · first seen 8 Oct 2026
centered kernel alignment
Also: CKA
Similarity index comparing internal representations between neural network layers.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Diagnosing Zero-Shot Forgetting in CLIP Fine-Tuning: Attention Drift Characterizes Adaptation, Representation Drift Predicts Transfer DegradationPapers · 8 Oct 2026 · Ruize Xia
- Surfing the Activation Wave: Analyzing the Information and Geometry of LLM Hidden States for Speculative DecodingPapers · 9 Oct 2026 · Raghavv Goel, Sudhanshu Agrawal, Mukul Gagrani, Risheek Garrepalli, Mingu Lee
- A Better Metric Will Not Save You: What You Compare Beats How You Compare ItPapers · 9 Oct 2026 · Noureddine Khaous, Guillaume Wisniewski
- Beyond Adjacent Layers: Graph-Guided Layer Fusion for Compressing Large Language ModelsPapers · 10 Oct 2026 · Muhammad Usama, Yeoreum Jung
- Measuring Learned Equivariance: An Information Theoretic ApproachPapers · 12 Oct 2026 · Claire Schlesinger, Wolfgang Gatterbauer, Robin Walters
- CAFE: Confining Feature Distillation to Language-Routed Adapters for Compact Multilingual Automatic Speech RecognitionPapers · 13 Oct 2026 · Tianchi Liu, Nicholas Moratelli, Khurram Azeem Hashmi, Mohammadreza Zolfaghari,…
Latest sources
- Classical structural priors improve neural molecular representations in molecule language modelsPapers · 16 Nov 2026 · Donghyeok Lee, Sangkwon Park, Munyoung Chang, Sungroh Yoon
- Unimodal Augmentation-based SSL Objectives Induce Cross-Modal AlignmentPapers · 2 Nov 2026 · Zohar Mashiah, Nir Ben-Ari, Ronen Talmon, Uri Shaham
- SlimFormer++: Token Mixing Where It Matters for Efficient 3D Medical Image SegmentationPapers · 18 Oct 2026 · Yang Hong, Lei Zhang, Zhihong Liu, Jianqing Mo, Xujiong Ye
- Null Controls Are Necessary but Not Sufficient: Evaluating Acceptance Guards for Scientific Discovery and InterpretabilityPapers · 15 Oct 2026 · Tianyu Wu
- CAFE: Confining Feature Distillation to Language-Routed Adapters for Compact Multilingual Automatic Speech RecognitionPapers · 13 Oct 2026 · Tianchi Liu, Nicholas Moratelli, Khurram Azeem Hashmi, Mohammadreza Zolfaghari,…
- Measuring Learned Equivariance: An Information Theoretic ApproachPapers · 12 Oct 2026 · Claire Schlesinger, Wolfgang Gatterbauer, Robin Walters
- Beyond Adjacent Layers: Graph-Guided Layer Fusion for Compressing Large Language ModelsPapers · 10 Oct 2026 · Muhammad Usama, Yeoreum Jung
- A Better Metric Will Not Save You: What You Compare Beats How You Compare ItPapers · 9 Oct 2026 · Noureddine Khaous, Guillaume Wisniewski
- Surfing the Activation Wave: Analyzing the Information and Geometry of LLM Hidden States for Speculative DecodingPapers · 9 Oct 2026 · Raghavv Goel, Sudhanshu Agrawal, Mukul Gagrani, Risheek Garrepalli, Mingu Lee
- Diagnosing Zero-Shot Forgetting in CLIP Fine-Tuning: Attention Drift Characterizes Adaptation, Representation Drift Predicts Transfer DegradationPapers · 8 Oct 2026 · Ruize Xia