Posters

This paper presents a novel watermarking scheme for language models that is both undetectable and robust to a constant fraction of adversarial edits (insertions, deletions, substitutions).

ECMamba: A novel dual-branch framework efficiently corrects multiple exposure images by integrating Retinex theory and an innovative 2D selective state-space layer, achieving state-of-the-art performa…

AI alignment beyond human supervision is achieved via easy-to-hard generalization: training reward models on easy tasks to effectively evaluate and improve generators on harder tasks, achieving superh…

E2, a novel regional contrastive learning method, enhances vision-language models for expressive fashion representations by explicitly attending to fashion details with minimal additional parameters, …

EASI: Evolutionary Adversarial Simulator Identification bridges the reality gap in robotics by using GAN and ES to find optimal simulator parameters, enabling seamless sim-to-real transfer with minima…

LLMs’ emotional decision-making is assessed using a novel framework, EAI, showing that emotions significantly alter ethical and strategic choices in games. This reveals crucial biases, necessitati…

EAGLE: A novel unsupervised cross-view adaptation method for semantic segmentation achieves state-of-the-art performance by efficiently modeling geometric structural changes across different camera vi…

E2ENet: A novel 3D medical image segmentation model boasts high accuracy and efficiency by dynamically fusing multi-scale features and using restricted depth-shift 3D convolutions, significantly outp…

E-Motion: Predicting future motion with unprecedented accuracy using event cameras and video diffusion models.

DynaMo: a novel self-supervised method significantly boosts visuo-motor control by learning in-domain dynamics from limited expert demonstrations, improving policy performance across various environme…

DynaMITE-RL: A new meta-RL approach masters environments with evolving latent states by cleverly modeling episode sessions and refining existing meta-RL techniques.

Researchers developed a novel stochastic-process approach to precisely analyze learning dynamics in nonlinear perceptrons, revealing how input noise and learning rules significantly impact learning sp…

Dynamic Tuning (DyT) significantly boosts Vision Transformer (ViT) adaptation by dynamically skipping less important tokens during inference, achieving superior performance with 71% fewer FLOPs than e…

A new dynamic subgroup identification strategy, using covariate-adjusted response-adaptive randomization, efficiently identifies best-performing subgroups in clinical trials, improving resource alloca…

This research introduces novel algorithms to dynamically price third-party platform service fees under strategic buyer behavior, achieving optimal revenue with a theoretically proven regret bound.

Dynamic rescaling boosts GNN training by controlling layer learning speeds and balancing networks, leading to faster training and improved generalization, especially on heterophilic graphs.

Dynamic Neural Regeneration (DNR) enhances deep learning generalization on small datasets using a data-aware dynamic masking scheme inspired by neurogenesis.

Dynamic Model Predictive Shielding (DMPS) ensures provably safe reinforcement learning by dynamically optimizing reinforcement learning objectives while maintaining provable safety, achieving higher r…

Simulation-free flow generates conditional distributions via dynamic conditional optimal transport.

Repeated cake-cutting game reveals that strategic players can exploit myopic opponents, but equitable outcomes are achievable through specific strategies.