Posters

Eye-gaze data boosts medical image-text alignment!

Researchers reveal a high risk of training data extraction from molecular pre-trained models, challenging the assumption that model sharing alone adequately protects against data theft.

This paper introduces a novel nonparametric method to make policy evaluations from randomized trials externally valid, even when trial and target populations differ. It leverages additional covariate…

Long-video masked autoencoders (LVMAE) achieve state-of-the-art performance by using an adaptive masking strategy that prioritizes important video tokens, enabling efficient training on 128 frames.

Ex-MCR: Efficiently build unified multi-modal representations by extending, not connecting, pre-trained spaces, achieving superior performance with less paired data and training.

EVA: a novel method generates expressive 3D Gaussian human avatars from monocular RGB videos, excelling in detailed hand and facial expressions via context-aware density control and improved SMPL-X al…

Quantum computing drastically reduces communication needs for distributed machine learning, enabling faster and more private AI.

XFADS: a novel low-rank structured VAE framework for large-scale nonlinear Gaussian state-space modeling, achieving high predictive accuracy and scalability.

This paper introduces a novel token pruning method for vision state space models, achieving significant computational reduction with minimal performance impact, addressing the limitations of directly …

KalmanNet, a novel BMI decoder, achieves state-of-the-art performance by integrating recurrent neural networks into Kalman filtering, balancing accuracy and explainability.

LLM-Infused Diffuser boosts text-to-image generation by smartly integrating LLMs, surpassing existing models in prompt understanding and image quality.

Single-layer GANs learn data subspaces more effectively using multi-feature discriminators, enabling faster training and better feature representation than conventional methods.

CE2: A new goal-directed exploration algorithm for efficient reinforcement learning in unknown environments, prioritizing accessible frontier goals via latent state clustering.

DUSA:Unlocking Diffusion Models’ Discriminative Power for Efficient Test-Time Adaptation

Uni-Mol2, a groundbreaking 1.1B parameter molecular pretraining model, reveals power-law scaling in molecular representation learning, achieving significant performance improvements on downstream task…

LOCO Edit achieves precise, localized image editing in diffusion models via a single-step, training-free method leveraging low-dimensional semantic subspaces.

This paper theoretically proves the existence and uniqueness of fixed points in DDIM inversion, optimizing the loss function for improved image editing and extending this approach to unsupervised imag…

FlowDCN: A purely convolutional generative model achieves state-of-the-art image generation speed and quality at arbitrary resolutions, surpassing transformer-based models.

Boost GNN graph classification accuracy by enforcing consistency in learned representations across layers using a novel loss function!

BeNeDiff uses generative diffusion models to disentangle and interpret neural dynamics linked to specific behaviors, providing interpretable quantifications of behavior in multi-brain region datasets.