Understanding Task Representations in Neural Networks via Bayesian Ablation

Documenti analoghi

• A Relational Inductive Bias for Dimensional Abstraction in Neural Networks
  di: Campbell, Declan, et al.
  Pubblicazione: (2024)
• Learning Human-Aligned Representations with Contrastive Learning and Generative Similarity
  di: Marjieh, Raja, et al.
  Pubblicazione: (2024)
• Causal Head Gating: A Framework for Interpreting Roles of Attention Heads in Transformers
  di: Nam, Andrew, et al.
  Pubblicazione: (2025)
• Human-Like Geometric Abstraction in Large Pre-trained Neural Networks
  di: Campbell, Declan, et al.
  Pubblicazione: (2024)
• Better World Models Can Lead to Better Post-Training Performance
  di: Gupta, Prakhar, et al.
  Pubblicazione: (2025)