PUICL is a transformer pretrained on synthetic PU data from structural causal models that solves positive-unlabeled classification via in-context learning without gradient updates or fitting.
Matteo Castiglioni, Andrea Celli, and Christian Kroer
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Inverse-RPO derives two variance-aware prior-based UCT policies from UCB-V that outperform PUCT on benchmarks with no extra cost.
A unified primal-dual framework learns latent linear treatment effect valuations and competitor bids in constrained first-price auctions, achieving near-optimal regret via strong Slater condition and adaptive burn-in.
Adding loop composition to branching quantum walk models produces a variable-time quantum search algorithm whose complexity matches the best known results.
Global Bradley-Terry rankings of LLMs are misleading due to structured heterogeneity in user preferences, and small (λ, ν)-portfolios recover coherent subpopulations that cover over 96% of votes with just five rankings.
The authors provide a systematization of differentially private graph release methods along with an objective-based framework and two illustrative evaluations for social network analysts.
citing papers explorer
-
In-Context Positive-Unlabeled Learning
PUICL is a transformer pretrained on synthetic PU data from structural causal models that solves positive-unlabeled classification via in-context learning without gradient updates or fitting.
-
Variance-Aware Prior-Based Tree Policies for Monte Carlo Tree Search
Inverse-RPO derives two variance-aware prior-based UCT policies from UCB-V that outperform PUCT on benchmarks with no extra cost.
-
Learning to Bid with Unknown Private Values in Budget-Constrained First-Price Auctions
A unified primal-dual framework learns latent linear treatment effect valuations and competitor bids in constrained first-price auctions, achieving near-optimal regret via strong Slater condition and adaptive burn-in.
-
Loop Composition in Quantum Algorithms
Adding loop composition to branching quantum walk models produces a variable-time quantum search algorithm whose complexity matches the best known results.
-
Why Global LLM Leaderboards Are Misleading: Small Portfolios for Heterogeneous Supervised ML
Global Bradley-Terry rankings of LLMs are misleading due to structured heterogeneity in user preferences, and small (λ, ν)-portfolios recover coherent subpopulations that cover over 96% of votes with just five rankings.
-
SoK: Practical Aspects of Releasing Differentially Private Graphs
The authors provide a systematization of differentially private graph release methods along with an objective-based framework and two illustrative evaluations for social network analysts.