We have 9 of 80 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
This work proposes a recursive offline distillation method combining two components: entropy-based sampling for selective distillation and answer mixing, and a comparative analysis of methods to generate and normalize distillation traces.
Kernel Mean Matching (KMM) estimates risk under covariate shift by reweighting labelled source samples so that their kernel mean embedding matches that of unlabeled target samples. Existing finite-sample guarantees are usually stated for independent samples, although many applications involve temporal, spatial, or clus...
Recent work has shown that probabilistic flow matching for time series forecasting benefits from a data-matched prior. The resulting prior introduces local correlations, which a sequential architecture usually absorbs: a recurrent neural network (RNN), a structured state-space model (S4), or a Transformer. However, suc...
Large-scale neural recommender systems are typically trained with a softmax cross-entropy objective over the full item vocabulary. For a typical large number of possible items $K$, the final classification layer dominates memory, requiring $O(nK)$ logits and gradients to materialize for a batch of $n$ examples. Sampled...
A GENerative ADversarial Attack (GENADA) is proposed that learns a generative model to produce deceptive perturbations directly in a single forward pass and a procedure to train it, and achieves comparable attack quality to strong baselines while requiring less time to generate perturbations during inference.
This work proposes CLaST, a VAE framework for probabilistic multivariate time series forecasting that learns embeddings that preserve contextual similarity between observations through the authors' contrastive loss function.
INTRYGUE (Induction-Aware Entropy Gating for Uncertainty Estimation), a training-free, mechanistically grounded method that gates predictive entropy by an attention-based estimate of induction-head activity, is proposed, suggesting that hallucination detection in RAG benefits from combining predictive uncertainty with...
DecoVAE is proposed, a lightweight interpretable trend-seasonal VAE framework that explicitly decomposes time series into trend and seasonal components by applying domain-specific inductive biases.
BEAR-Bench (Bilingual Enterprise and Academic Reasoning), a self-contained, complex English-and-Russian benchmark comprising 1000 human-annotated questions based on text-rich business and scientific documents, is introduced, and existing hallucination detection methods are compared.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
