Model Theory, Proof Theory, Completeness, Decidability
DeBackdoor: A Deductive Framework for Detecting Backdoor Attacks on Deep Models with Limited Data
usenix.org·1d
Effective Noisy-matrix of Bayesian network for scalable <em>m-</em>Consecutive<em>-k-</em>out-of<em>-n</em>: F models with overlapping from -1 to <em>k-</em>1
sciencedirect.com·2d
Integrating Feature Attention and Temporal Modeling for Collaborative Financial Risk Assessment
arxiv.org·6h
Silicon Minds versus Human Hearts: The Wisdom of Crowds Beats the Wisdom of AI in Emotion Recognition
arxiv.org·1d
Resurrecting the Salmon: Rethinking Mechanistic Interpretability with Domain-Specific Sparse Autoencoders
arxiv.org·6h
Multi-head Transformers Provably Learn Symbolic Multi-step Reasoning via Gradient Descent
arxiv.org·2d
Fine-Grained Safety Neurons with Training-Free Continual Projection to Reduce LLM Fine Tuning Risks
arxiv.org·6h
Loading...Loading more...