Posters

POSEIDON: a novel foundation model for PDEs achieves significant gains in accuracy and sample efficiency, generalizing well to unseen physics.

This paper presents a novel method for analytically extracting meshes from neural implicit surface networks using trilinear interpolation, offering theoretical insights and practical efficiency.

Policy-Shaped Prediction (PSP) improves model-based reinforcement learning by focusing world models on task-relevant information, significantly enhancing robustness against distracting stimuli.

First-order policy optimization for robust average-cost MDPs achieves linear convergence with increasing step size and 0(1/ε) complexity with constant step size, solving a critical gap in existing res…

Boosting reinforcement learning, this paper introduces h-PMD, a novel algorithm enhancing policy mirror descent with lookahead for faster convergence and improved sample complexity.

Boosting AI instruction following, Language Feedback Models (LFMs) leverage Large Language Models (LLMs) to identify desirable behaviors from visual trajectories, significantly improving task completi…

This paper introduces efficient algorithms that leverage social choice theory to aggregate multiple individual preferences, resulting in a desirable collective AI policy.

PointMamba: A linear-complexity state space model achieving superior performance in point cloud analysis, reducing computational cost significantly.

PointAD: a novel zero-shot 3D anomaly detection method using CLIP’s strong generalization abilities to identify anomalies in unseen objects by transferring knowledge from both points and pixels.

Point-PRC improves generalizable 3D point cloud analysis by regulating prompt learning to harmonize task-specific and general knowledge within large 3D models.

PLIP: Novel language-image pre-training framework excels at person representation learning, surpassing existing methods on various downstream tasks thanks to its three pretext tasks and large-scale SY…

Learning-augmented mechanisms for fair allocation achieve constant-factor approximation with accurate predictions and near-optimal approximation even with inaccurate ones.

Plan-on-Graph (PoG) revolutionizes KG-augmented LLMs with a self-correcting adaptive planning paradigm, enabling more efficient and accurate reasoning over knowledge graphs by dynamically adjusting ex…

PIVOT-R, a novel primitive-driven waypoint-aware world model, significantly boosts robotic manipulation performance and efficiency via an asynchronous hierarchical executor.

New pipeline parallelism framework achieves up to 55% higher throughput and 50% less memory usage in large language model training by systematically controlling activation memory.

Pin-Tuning: A parameter-efficient method for few-shot molecular property prediction that significantly improves accuracy with fewer trainable parameters via in-context tuning and Bayesian weight cons…

A novel inventory reserving algorithm achieves near-optimal performance for bandit problems with knapsacks in piecewise-stationary settings, offering a competitive ratio of O(log(nmax/min)).

Novel generative models based on piecewise deterministic Markov processes (PDMPs) are introduced, offering efficient training procedures and theoretical guarantees, surpassing diffusion-based models i…

Physics-regularized multi-modal image assimilation improves brain tumor localization by integrating data-driven and physics-based cost functions, achieving state-of-the-art performance in capturing tu…

PHYSS-GP: a novel physics-informed state-space Gaussian process model for efficient spatio-temporal data modeling, outperforming existing methods in predictive accuracy and computational speed.