Posters

DeepITE: a novel variational graph autoencoder, efficiently estimates intervention targets from both labeled and unlabeled data, surpassing existing methods in recall and inference speed.

DeepDRK, a novel deep learning approach, significantly improves feature selection by effectively balancing false discovery rate and power, surpassing existing methods, especially with limited data.

Deep RL excels in simulated robotics, but struggles with real-world limitations like limited computational resources. This paper introduces Action Value Gradient (AVG), a novel incremental deep polic…

Deep linear networks implicitly regularize towards flat minima, with sharpness (Hessian’s largest eigenvalue) of minimizers linearly increasing with depth but bounded by a constant times the lower bou…

A simple, yet accurate model unveils deep learning’s mysteries, providing empirical insights into grokking, double descent, and gradient boosting, offering a new lens for analyzing neural network beha…

Deep learning (DL) image registration methods sometimes underperform classical methods, especially when data distribution shifts; this study reveals when each approach excels.

Deep Homomorphism Networks (DHNs) boost graph neural network (GNN) expressiveness by efficiently detecting subgraph patterns using a novel graph homomorphism layer.

PSNR, a novel node-adaptive residual module, significantly improves deep GNN performance by mitigating over-smoothing and handling missing data.

Deep Graph Mating (GRAMA) enables training-free knowledge transfer in GNNs, achieving results comparable to pre-trained models without retraining or labeled data.

Deep Equilibrium Algorithmic Reasoners (DEARs) achieve superior performance on algorithmic tasks by directly solving for the equilibrium point of a neural network, eliminating the need for iterative r…

Deep Correlated Prompting enhances large multimodal models’ robustness against missing data by leveraging inter-layer and cross-modality correlations in prompts, achieving superior performance with mi…

BAL-PM, a novel active learning approach, drastically reduces human feedback in LLM preference modeling by leveraging both model uncertainty and prompt distribution diversity, achieving 33%-68% fewer …

DECRL: A novel deep learning approach for temporal knowledge graph representation learning, capturing high-order correlation evolution and outperforming existing methods.

Researchers developed semantic RSMs, a novel approach to measure semantic similarity in neural networks, improving image retrieval and aligning network representations with predicted class probabiliti…

Improved Kullback-Leibler (IKL) divergence loss achieves state-of-the-art adversarial robustness and competitive knowledge distillation performance by addressing KL loss’s limitations.

This paper presents a general framework for interpreting Vision Transformer (ViT) components, mapping their contributions to CLIP space for textual interpretation, and introduces a scoring function fo…

Decomposed Prompt Decision Transformer (DPDT) efficiently learns prompts for unseen tasks using a two-stage paradigm, achieving superior performance in multi-task offline reinforcement learning.

Decomposable Transformer Point Processes (DTPP) dramatically accelerates marked point process inference by using a mixture of log-normals for inter-event times and Transformers for marks, outperformin…

Multi-objective decoding (MOD) efficiently aligns language models to diverse user needs by decoding the next token from a weighted combination of predictions from multiple base models trained on indiv…

New framework reveals LLMs’ human-like decision-making tendencies but highlights significant variations and biases influenced by demographic factors, underscoring ethical deployment needs.