Posters

AdaNeg dynamically generates negative proxies during testing to improve vision-language model OOD detection, significantly outperforming existing methods on ImageNet.

Boosting Vision Transformer robustness against attacks & noisy data, AdaNCA uses Neural Cellular Automata as plug-and-play adaptors between ViT layers, achieving significant accuracy improvement with …

Clipped Adam with EMA achieves optimal convergence rates for smooth and non-smooth nonconvex optimization, particularly when scales vary across different coordinates.

Adam-Rel: A novel optimizer for RL, dramatically improves performance by resetting Adam’s timestep to 0 after target network updates, preventing large, suboptimal changes.

AdaFlow: a novel imitation learning framework boasts fast inference and diverse action generation via variance-adaptive flow-based policies, significantly outperforming existing methods.

Ada-MSHyper: A novel adaptive multi-scale hypergraph transformer significantly boosts time series forecasting accuracy by modeling group-wise interactions and handling complex temporal variations.

This paper introduces segment auctions, maximizing logarithmic social welfare, for integrating ads into LLM outputs via Retrieval Augmented Generation, balancing ad revenue and output quality.

ActSort: Active learning dramatically accelerates cell sorting in massive calcium imaging datasets, minimizing human effort and improving accuracy.

This paper introduces anytime-valid risk-controlling prediction sets for active learning, guaranteeing low risk even with adaptive data collection and limited label budgets.

Active Set Ordering: Efficiently discover input subsets (maximizers, top-k) of expensive black-box functions via pairwise comparisons, using a novel Mean Prediction algorithm with theoretical guarante…

Active Sequential Neural Posterior Estimation (ASNPE) boosts simulation-based inference efficiency by actively selecting informative simulation parameters, significantly outperforming existing methods…

Active learning efficiently orders items using contextual attributes, minimizing comparison needs and improving generalization.

ActiveNGF achieves superior robotic grasping by using a Neural Graspness Field to model scene grasp distribution online, enabling efficient camera movement and improved grasp pose detection.

Active learning for general halfspaces is surprisingly hard; membership queries are key to efficiency.

Boost global sensitivity analysis efficiency by 10x with novel active learning methods targeting derivative-based measures for expensive black-box functions!

Researchers developed an active learning method using two-photon holographic optogenetics to efficiently identify neural population dynamics, achieving up to a two-fold reduction in data needed for ac…

Slash deep learning’s memory footprint! This paper introduces a novel activation map compression technique via tensor decomposition, significantly boosting on-device training efficiency for edge AI.

Boosting Multi-Scene Pose Regression: Novel methods activate transformer self-attention, significantly improving camera pose estimation accuracy and efficiency.

TwinAct: Decoupling actions and actors for customizable text-guided action image generation.

Distributional RL’s sensitivity to high-frequency decisions is unveiled, with new algorithms solving existing performance issues in continuous-time RL.