Posters

PeRFlow accelerates diffusion models by straightening their sampling trajectories using a piecewise reflow operation, enabling fast and high-quality image generation with minimal computational cost.

This study reveals that large language models struggle with semi-open-ended questions, often hallucinating or providing insufficient answers. Researchers explored this by creating a new dataset of su…

BiXT, a novel bi-directional cross-attention Transformer, scales linearly with input size, achieving competitive performance across various tasks by efficiently processing longer sequences.

This paper proposes penalty-based methods for simple bilevel optimization, achieving (ε, εβ)-optimal solutions with improved complexity under Hölderian error bounds.

PediatricsGPT: a novel Chinese pediatric LLM assistant trained on a large, high-quality dataset (PedCorpus) outperforms existing models, paving the way for improved pediatric healthcare.

New Pedestrian-Vehicle Collision Pose dataset (PVCP) and Pose Estimation Network (PPSENet) improve pedestrian pre-collision pose estimation from dashcam video.

Colander: a novel auto-labeling technique boosts data efficiency by 60%, optimizing confidence functions for maximum coverage with minimal error.

PEAC: a novel unsupervised pre-training method significantly improves cross-embodiment generalization in reinforcement learning, enabling faster adaptation to diverse robots and tasks.

PCoTTA: A novel framework enables multi-task point cloud models to seamlessly adapt to continuously changing target domains during testing, overcoming catastrophic forgetting and error accumulation.

pcaGAN boosts posterior-sampling cGANs by using principal component regularization, achieving faster, more accurate results in various imaging tasks.

µPOCA: a new active learning approach maximizes model generalization using strategically acquired labels/features in data-scarce, costly scenarios with partial observability, leveraging LLMs for effic…

This paper introduces a novel technique to bound prediction risks in new domains using causal diagrams, enabling reliable AI performance guarantees.

Learning optimal interventions in causal bandits with unknown causal graphs is now efficient; this paper identifies the minimal causal knowledge needed and offers a two-stage algorithm with sublinear …

Partially observing neural circuits during experiments can create misleading models, even if single neuron activity matches; researchers need better validation methods.

Boost continual reinforcement learning with Parseval regularization: maintaining orthogonal weight matrices preserves optimization, significantly improving RL agent training across diverse tasks.

PARD: a novel permutation-invariant autoregressive diffusion model for efficient and high-quality graph generation, achieving state-of-the-art results.

HOAM learns reduced models of population dynamics for complex systems, enabling fast predictions across various physics parameters, outperforming state-of-the-art techniques.

First parameterized approximation schemes for fair-range k-median & k-means in Euclidean spaces are presented, offering faster (1+ε)-approximation algorithms.

Parameter-free optimization is revolutionized! Inexact Polyak Stepsize achieves the same convergence rate as clipped gradient descent but without any hyperparameter tuning, saving time and computatio…

SGD’s dynamics are precisely characterized by the interplay of noise and symmetry in loss functions, leading to unique, initialization-independent fixed points.