Posters

DMNet: A novel self-comparison driven model significantly improves subject-independent seizure detection from intracranial EEG, outperforming existing methods.

DMesh: A novel differentiable mesh representation enabling efficient gradient-based optimization for diverse 3D shape applications.

DALD: A novel framework for black-box LLM text detection, achieving state-of-the-art performance without relying on source model logits, by aligning surrogate model distributions.

Divide-and-conquer predictive coding (DCPC) revolutionizes structured Bayesian inference by achieving superior performance in high-dimensional problems while remaining biologically plausible.

Divide-and-Conquer Posterior Sampling (DCPS) efficiently samples complex posterior distributions from denoising diffusion models (DDMs) for Bayesian inverse problems, significantly improving accuracy …

Training robust cooperative AI agents requires diverse and specialized training partners, but existing methods often produce overfit partners. This paper proposes novel methods using reinforcement and…

Language models struggle with social/emotional intelligence and physical commonsense, unlike human brains. Fine-tuning models on these aspects improves their brain response prediction accuracy.

DiTFastAttn: A post-training compression method drastically speeds up diffusion transformer models by cleverly reducing redundancy in attention calculations, leading to up to a 1.8x speedup at high re…

DISTRICTNET: A novel decision-aware learning approach drastically cuts geographical districting costs by integrating combinatorial optimization and graph neural networks.

Provably sample-efficient robust RL via interactive data collection is achieved by introducing the vanishing minimal value assumption to mitigate the curse of support shift, enabling near-optimal algo…

This research introduces distributionally robust performative prediction, offering a new solution concept (DRPO) that minimizes performative risk even with misspecified distribution maps, ensuring rob…

DiSPOs: a novel model for zero-shot policy optimization in reinforcement learning, enabling quick adaptation to new tasks by learning a distribution of successor features and avoiding compounding erro…

Sinkhorn distributional RL (SinkhornDRL) uses a regularized Wasserstein loss to improve distributional reinforcement learning.

This paper provides the first statistical learning guarantees for distributional regression using CRPS, offering concentration bounds for model fitting, selection, and convex aggregation, applicable t…

LLMs are aligned to human preferences distributionally using Optimal Transport, achieving state-of-the-art performance.

DistDiff, a training-free data expansion framework, leverages distribution-aware diffusion models to generate high-fidelity, diverse samples that enhance downstream model performance.

Generative models often produce invalid outputs; this work shows that ensuring validity is easier than expected when using log-loss and carefully selecting model classes and data distributions.

DGNet enhances weakly supervised point cloud segmentation by aligning feature embeddings to a mixture of von Mises-Fisher distributions, achieving state-of-the-art performance.

Researchers developed a novel sparse sketching method for distributed least squares regression, achieving near-unbiased estimates with optimal space and time complexity.

DistillNeRF: a self-supervised learning framework enabling accurate 3D scene reconstruction from sparse, single-frame images by cleverly distilling features from offline NeRFs and 2D foundation models…