Genre
Efficient Availability Attacks against Supervised and Contrastive Learning Simultaneously
Ideally, the obtained unlearnability can prevent algorithms from training usable models.
SeT AR: Out-of-Distribution Detection with Selective Low-Rank Approximation
SeT AR enhances OOD detection via post-hoc modification of the model's
Order-Independence Without Fine Tuning
Reid McIlroy-Young, Katrina Brown, Conlan Olson, Linjun Zhang, Cynthia Dwork
Unlike humans, these ' Large Language Models ' (LLMs) are highly sensitive to small changes in their inputs, leading to unwanted inconsistency in their behavior.
Marginal Density Ratio for Off-Policy Evaluation in Contextual Bandits Muhammad Faaiz Taufiq
Propensity Score (MIPS) estimator, proving that MR achieves lower variance among a generalized family of MIPS estimators.
Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers Lorenzo Tiberi 1,2 Francesca Mignacco
Second, generalization--what specific aspects of the transformer architecture are responsible for their effective learning?