Posters

Grid4D: A novel 4D decomposed hash encoding boosts high-fidelity dynamic Gaussian splatting, surpassing state-of-the-art models in visual quality and rendering speed.

GREAT Score: A novel framework using generative models for efficiently and accurately evaluating the global robustness of machine learning models against adversarial attacks.

Deep neural networks surprisingly exhibit universal convergence in input salience, aligning more closely as model capacity increases, revealing valuable insights into model behavior and improving deep…

Robots can now dexterously grasp objects based on natural language commands thanks to DexGYS, a new language-guided dexterous grasp generation framework and dataset.

GraphVis boosts LLMs by visualizing knowledge graphs, improving accuracy in textual and visual question answering.

GRAPHTRAIL unveils the first end-to-end global GNN explainer, translating black-box GNN predictions into easily interpretable boolean formulas over subgraph concepts, achieving significant improvement…

GraphMorph: revolutionizing tubular structure extraction by morphing predicted graphs for superior topological accuracy.

GraphMETRO tackles complex graph distribution shifts by using a Mixture-of-Experts model to decompose shifts into interpretable components, achieving state-of-the-art results.

GraphCroc, a novel graph autoencoder, leverages cross-correlation to accurately reconstruct complex graph structures, outperforming self-correlation-based methods.

Graphcodes efficiently summarize complex datasets’ topological properties using graph neural networks, enhancing machine learning accuracy.

SEvo, a novel embedding update mechanism, directly injects graph structural information into recommendation embeddings, boosting performance significantly while avoiding the computational overhead of …

GEM, a novel framework, uses a bidirectional graph and MLLMs to achieve fine-grained, relation-aware disentanglement in unsupervised representation learning, surpassing existing methods.

Boost GNN performance and overcome oversmoothing with Cluster-Normalize-Activate (CNA) modules: a simple yet highly effective plug-and-play solution!

Deep graph neural networks often suffer from oversmoothing; this paper reveals a non-oversmoothing phase controllable by weight variance, enabling deep, expressive models.

Graph Neural Networks’ (GNNs) computational power precisely mirrors that of arithmetic circuits, as proven via a novel C-GNN model; this reveals fundamental limits to GNN scalability.

GNeuralFlow unveils systemic interactions in irregularly sampled time series by learning a directed acyclic graph representing conditional dependencies, achieving superior performance in classificatio…

GOOSE: a novel framework using graph learning for efficient and interpretable numeric planning, outperforming existing methods in many benchmarks.

GRAPHEDX, a novel neural network, accurately estimates graph edit distance with varying operation costs, outperforming existing methods.

GDPO: A novel method optimizes graph diffusion models for any objective using reinforcement learning, achieving state-of-the-art performance in diverse graph generation tasks.

Graph Filter-based Self-Attention (GFSA) enhances Transformers by addressing oversmoothing, boosting performance across various tasks with minimal added parameters.