Posters

Conformal prediction empowers robust credal set predictions, handling aleatoric and epistemic uncertainties in classification, guaranteed to be valid with high probability!

RC3P, a novel algorithm, significantly reduces prediction set sizes in class-conditional conformal prediction while guaranteeing class-wise coverage, even on imbalanced datasets.

Conformal inverse optimization learns uncertainty sets for parameters in optimization models, then solves a robust optimization model for high-quality, human-aligned decisions.

This paper introduces AFCP, a novel conformal inference method that generates prediction sets with valid coverage conditional on adaptively selected features, achieving a practical balance between eff…

Conformal Alignment certifies trustworthy foundation model outputs by guaranteeing a user-specified fraction meet alignment criteria, regardless of the model or data.

Confident-NPG-CMDP: First primal-dual algorithm achieving polynomial sample complexity for solving constrained Markov decision processes (CMDPs) using function approximation and local access model.

LLMs regulate uncertainty via specialized ’entropy’ and ’token frequency’ neurons, impacting prediction confidence without directly altering logits.

Boost multi-class classifier calibration by cleverly transforming the problem into a single binary calibration task!

CondTSF: One-line plugin for time series forecasting dataset condensation, boosting performance at low condensation ratios.

Researchers introduce the Conditional Quantile Comparator (CQC) for analyzing heterogeneous treatment effects, offering an improved approach by combining the strengths of CATE and CQTE while overcomin…

ID-GEN: Sample high-dimensional interventional distributions using any conditional generative model!

Conditional Controllable Fusion (CCF) achieves training-free, adaptable image fusion by dynamically injecting fusion conditions into a pre-trained denoising diffusion model.

Boost language model performance across domains with ‘Concentration’: a new prompt optimization objective that prioritizes stable, deep-layer attention.

Con4m, a novel consistency learning framework, leverages contextual information to effectively classify segmented time series with inconsistent boundary labels and varying durations of classes, signif…

New method quantifies & reduces bias in constant-step stochastic approximation algorithms with Markovian noise, improving accuracy and efficiency.

Collaborative Computerized Adaptive Testing (CCAT) improves student ranking accuracy in online exams by leveraging inter-student information to enhance ranking consistency.

This paper presents efficient algorithms for Bayesian persuasion under approximate best response, offering polynomial-time solutions for specific cases and a quasi-polynomial-time approximation scheme…

Computation-Aware Gaussian Processes (CaGP) achieve linear-time inference and model selection, enabling efficient training of GPs on large datasets without compromising uncertainty quantification, sur…

CALDERA: a new post-training LLM compression algorithm achieving state-of-the-art zero-shot performance using low-rank, low-precision decomposition.

Novel compositional PAC-Bayes framework delivers data-dependent generalization bounds for persistence-enhanced Graph Neural Networks, improving model design and performance.