Deep Learning
ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence
GPT -4o, on this dataset and find that LLMs are susceptible to adopting incorrect retrieved content, overriding their own correct prior knowledge over 60% of the time. However, the more unrealistic the retrieved content is (i.e. more deviated from
Beyond the Single Neuron Convex Barrier for Neural Network Certification
Gagandeep Singh, Rupanshu Ganvir, Markus Pรผschel, Martin Vechev
Neural Information Processing Systems http://nips.cc/
Learning Stable Deep Dynamics Models
Neural Information Processing Systems http://nips.cc/
d87ca511e2a8593c8039ef732f5bffed-Supplemental.pdf
Weprovethat under mild conditions there is no vanishing or exploding gradient in training SBO-RNN.
Pseudo-Private Data Guided Model Inversion Attacks
In model inversion attacks (MIAs), adversaries attempt to recover the private training data by exploiting access to a well-trained target model.
Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecasting
Recently, deep models have achieved great success in time series forecasting.
Structuring UncertaintyforFine-GrainedSampling inStochasticSegmentationNetworks
Weobtain them directly from the low-rank Gaussian distribution for the logits in the network head of SSNs, based on a previously unconsidered view of this distribution as a factor model.