PulseAugur
EN
LIVE 15:38:49
ENTITY Concept Activation Vectors

Concept Activation Vectors

PulseAugur coverage of Concept Activation Vectors — every cluster mentioning Concept Activation Vectors across labs, papers, and developer communities, ranked by signal.

Show in brief
Total · 30d
1
3 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
1
3 over 90d
TIER MIX · 90D
TOPICS
SENTIMENT · 30D

1 day(s) with sentiment data

RECENT · PAGE 1/1 · 5 TOTAL
  1. RESEARCH · CL_242952 ·

    ExpertLens framework visualizes MoE embedding spaces for better retrieval explainability

    Researchers have introduced ExpertLens, a novel framework designed to enhance the explainability of Mixture-of-Experts (MoE) enhanced dense retrievers used in information retrieval. Unlike existing methods that focus on…

  2. TOOL · CL_187254 ·

    New method probes bias in AI L2 speaking assessment systems

    Researchers have developed a new method to analyze bias in AI systems used for second language (L2) speaking assessments. This approach utilizes Concept Activation Vectors (CAVs) to probe how models like BERT and Whispe…

  3. TOOL · CL_174313 ·

    New framework explains image similarity using concept activation vectors

    Researchers have developed a new framework to explain image similarity using automatically extracted Concept Activation Vectors (CAVs). This model-agnostic approach utilizes Sparse Autoencoders (SAEs) to identify concep…

  4. TOOL · CL_51554 ·

    New method steers physics reasoning in video world models

    Researchers have developed a method called physics steering to control the physical reasoning of video world models. This technique uses a linear probe's weight vector, identified as a Concept Activation Vector (CAV), w…

  5. RESEARCH · CL_36337 ·

    New framework enhances stability of deep learning concept explainability

    Researchers have introduced $\alpha$-TCAV, a new framework designed to improve the statistical stability and practical utility of Concept Activation Vectors (CAVs) in deep learning explainability. The proposed method ad…