Posters

DSPoser: A novel two-stage approach accurately estimates full-body pose from doubly sparse egocentric video data using masked autoencoders for temporal completion and conditional diffusion models for …

ESPACE: A novel LLM compression technique achieving 50% model size reduction with minimal accuracy loss by cleverly projecting activations onto principal components.

Boosting neural network robustness against weight errors, this research leverages neural tangent kernels to theoretically explain and optimize error-correcting output codes (ECOCs), achieving superior…

This research paper presents a novel theoretical error analysis for the spherically constrained least squares (SCLS) method used to solve Stackelberg prediction games (SPGs). SPGs model strategic int…

This research introduces adversarial concept preservation, a novel method for safely erasing undesirable concepts from diffusion models, outperforming existing techniques by preserving related sensiti…

Era3D: High-resolution multiview diffusion using efficient row-wise attention, generates high-quality multiview images from single views, overcoming prior limitations.

Faster, more efficient deep learning for diffusion MRI deconvolution is achieved using spatio-hemispherical networks, improving fiber tractography.

Equivariant Neural Diffusion (END) revolutionizes 3D molecule generation with a learnable forward process, achieving state-of-the-art results and enhanced controllability.

Nonlinear spectral filters (NLSFs) enable fully equivariant graph neural networks, improving accuracy and generalization.

Equivariant Blurring Diffusion (EBD) generates 3D molecular conformers hierarchically, first creating coarse-grained fragments then refining atomic details, significantly outperforming existing method…

RL agents make better decisions by simulating future scenarios, considering diverse agent behaviors, and using character inference for improved decision-making.

eFreeSplat: a novel, epipolar-free 3D Gaussian splatting model for generalizable novel view synthesis, surpassing state-of-the-art methods by achieving superior geometry reconstruction and novel view …

EPIC: Effective prompting makes LLMs generate high-quality synthetic tabular data, significantly boosting imbalanced-class classification.

This paper provides novel entrywise error bounds for low-rank kernel matrix approximations, showing how many data points are needed to get statistically consistent results for low-rank approximations.

Entropy-regularized diffusion policy with Q-ensembles achieves state-of-the-art offline reinforcement learning by tackling overestimation of Q-values and boosting exploration.

This paper presents near-optimal algorithms for entropy identity testing, significantly improving Bayesian network testing efficiency.

LLM4EA: A novel framework efficiently merges knowledge graphs using LLMs, overcoming noisy annotations and high costs via active learning and unsupervised label refinement, boosting accuracy and effic…

EnsIR: Training-free image restoration ensemble via Gaussian mixture models, boosting accuracy efficiently.

Small ensembles in stochastic linear bandits achieve near-optimal regret; a rigorous analysis shows that ensemble size need only scale logarithmically with horizon.

This paper presents a novel approach to deriving theoretically grounded disentanglement metrics by linking logical definitions to quantitative measures, offering strong theoretical guarantees and easi…