Posters

CP3ER, a novel consistency policy with prioritized proximal experience regularization, significantly boosts sample efficiency and stability in visual reinforcement learning, achieving state-of-the-art…

QGCNs generalize CNNs to graph data via learnable neighborhood quantization, achieving state-of-the-art performance on graph datasets.

This paper proposes Functional t-SVD and ERM-DS to solve multi-output regression under Combinatorial Distribution Shift (CDS), providing robust performance guarantees.

This paper presents a novel method for fast and exact conformalization, leveraging inherent piecewise smoothness to dramatically accelerate uncertainty quantification in machine learning models.

This research presents a novel method for robust semantic segmentation, achieving state-of-the-art results by generating coherent images with both semantic and covariate shifts and recalibrating uncer…

New, tighter generalization bounds are derived for a class of stochastic learning algorithms that generate absolutely continuous probability distributions; enhancing our understanding of their perform…

New information-theoretic generalization bounds, based on conditional f-information, improve existing methods by addressing unboundedness and offering a generic approach applicable to various loss fun…

Learn to project, solve faster! This paper introduces data-driven projections for solving high-dimensional linear programs, proving theoretical guarantees and demonstrating significant improvements in…

Unlocking deep learning’s generalization mystery, this research pioneers a theoretical understanding of memorization neural network generalizability, revealing critical network structural requirements…

Balancing Alignment and Uniformity (BAU) framework improves generalizable person re-identification by mitigating the polarized effects of data augmentation, achieving state-of-the-art performance.

Generalizable Implicit Motion Modeling (GIMM) revolutionizes video frame interpolation by accurately predicting optical flows at any timestep, surpassing existing methods and achieving state-of-the-ar…

One-shot animatable head avatar reconstruction is achieved using a novel dual-lifting method that generates 3D Gaussians from a single image, enabling real-time expression control and rendering with s…

A novel detection-based approach (DTLR) achieves state-of-the-art text line recognition across diverse scripts (Latin, Chinese, ciphers), overcoming challenges of character-level annotation and comple…

New theoretical bounds on Bayesian coreset approximation errors enable efficient large-scale Bayesian inference, overcoming prior limitations and improving coreset construction methods.

Part-Aware Diffusion Model (PA-Diffusion) enables precise and efficient manipulation of articulated objects in real images by using abstract 3D models and dynamic feature maps, overcoming limitations …

Novel imputation method, scCR, leverages complete gene-gene relationships (associating & dissociating) for superior single-cell RNA sequencing data recovery, significantly outperforming current state-…

GDeR: A novel dynamic graph pruning method boosts GNN training efficiency and robustness by intelligently selecting a representative subset of training data, mitigating issues caused by imbalanced or …

GAVEL uses AI to evolve novel board games by mutating and recombining game rules encoded in a sophisticated game description language.

GaussianMarker: A novel uncertainty-aware watermarking method ensures robust copyright protection for 3D Gaussian Splatting assets, invisibly embedding messages into model parameters and extractable …

GaussianCut enables intuitive 3D object selection via graph cuts on 3D Gaussian splatting, achieving competitive segmentation without extra training.