Posters

LMSPS: a novel framework efficiently leverages long-range dependencies in large heterogeneous graphs by dynamically identifying effective meta-paths, mitigating computational costs and over-smoothing.

Long-range feedback spiking network (LoRaFB-SNet) surpasses other models in capturing dynamic and static visual cortical representations under movie stimuli, advancing our understanding of visual syst…

ALTER, a novel brain graph transformer, leverages long-range dependencies to achieve state-of-the-art accuracy in neurological disease diagnosis.

LLaMAR: LM-based planner for multi-agent robots excels in long-horizon, partially observable tasks, achieving 30% higher success than existing methods.

LLMs often generate factually inaccurate long-form text. This work introduces LongFact, a new benchmark dataset of 2280 fact-seeking prompts, and SAFE, a novel automated evaluation method that outperf…

Loki: Low-rank Keys for Efficient Sparse Attention accelerates attention mechanisms in LLMs by exploiting the low-dimensionality of key vectors. It dynamically selects key tokens based on approximate…

Recurrent Graph Neural Networks (GNNs) with real and floating-point numbers are precisely characterized by rule-based and infinitary modal logics, respectively, enabling a deeper understanding of thei…

This paper introduces robust Dikin walks for log-concave sampling, achieving faster mixing times and lower iteration costs than existing methods, particularly for high-dimensional settings.

LOFIT: Localized fine-tuning boosts LLMs’ performance by selectively training only a small subset of attention heads, achieving comparable accuracy to other methods while using significantly fewer par…

LoD-Loc: A novel aerial visual localization method uses lightweight LoD 3D maps & neural wireframe alignment for accurate and efficient 6-DoF pose estimation, surpassing state-of-the-art methods.

LoCo: Memory-efficient location-consistent image features learned via a novel ranking loss, enabling three orders of magnitude memory improvement and outperforming state-of-the-art.

LocCa, a novel visual pretraining paradigm, uses location-aware captioning tasks to boost downstream localization performance while maintaining holistic task capabilities.

CATOD framework improves text-to-image generation by actively learning high-quality training data to accurately depict out-of-distribution concepts.

This research unveils a fundamental interplay between local differential privacy (LDP) and robustness against data corruption and heavy-tailed rewards in multi-armed bandits, offering a tight characte…

SSL vision encoders, while trained on massive datasets, surprisingly memorize individual data points. This paper introduces novel methods to precisely pinpoint this memorization within encoders at bot…

Localized Adaptive Risk Control (L-ARC) improves fairness and reliability of online prediction by providing localized statistical risk guarantees, surpassing existing methods in high-stakes applicatio…

LucidDrag: Semantic-aware dragging transforms image editing with an intention reasoner and collaborative guidance, achieving superior accuracy, image fidelity, and semantic diversity.

Transformers’ learning dynamics depend heavily on initialization and Markovian data properties, leading to either global or local minima; this paper proves this, offers initialization guidelines, and …

Local Superior Soups (LSS) significantly accelerates federated learning by efficiently merging pre-trained models, drastically cutting communication rounds without sacrificing accuracy.

CINDERELLA: a new algorithm achieves state-of-the-art no-regret bounds for continuous RL problems by exploiting local linearity.