Posters

DFA-GNN: A novel forward learning framework for GNNs enhances training efficiency and robustness by directly aligning feedback signals, outperforming traditional methods.

DEX boosts CNN accuracy on tiny AI accelerators by 3.5%p, utilizing unused memory and processors to extend input channels without increasing latency.

DeTrack revolutionizes visual object tracking with an in-model latent denoising learning process, achieving real-time speed and state-of-the-art accuracy.

MOMBO: a novel offline reinforcement learning algorithm that uses deterministic uncertainty propagation for faster convergence and tighter suboptimality bounds.

This paper presents an efficient algorithm to compute near-optimal deterministic policies for constrained reinforcement learning problems, solving a 25-year-old computational complexity challenge.

DeTeCtive: a novel multi-task contrastive learning framework, achieves state-of-the-art AI-generated text detection by distinguishing diverse writing styles instead of simple binary classification.

Hybrid LLM & rule-based system accurately detects costly smart contract bugs!

Deep learning models’ robustness can be efficiently evaluated using a novel method, margin consistency, which leverages the correlation between input and logit margins for faster, accurate vulnerabili…

This paper proposes novel measures to detect and quantify confounding biases from observational data using causal mechanism shifts, even with unobserved confounders.

DETAIL: A novel attribution method reveals the impact of individual demonstrations in in-context learning, boosting interpretability and improving transformer-based model performance.

Boosting Human-AI teamwork via interactive, explainable AI!

Researchers developed a data-efficient method using conservative model-based optimization to design cell-type-specific promoters for gene therapy, significantly improving cell-type specificity.

Stochastic gradient descent’s derivatives, crucial for hyperparameter optimization, converge to the solution mapping derivative; rates depend on step size, exhibiting O(log(k)²/k) convergence with van…

Derivative-enhanced DeepONets boost PDE solution accuracy and derivative approximation, particularly valuable with limited training data.

Derandomizing multi-distribution learning is computationally hard, but a structural condition allows efficient black-box conversion of randomized predictors to deterministic ones.

Depth Anywhere enhances 360-degree monocular depth estimation by cleverly using perspective models to label unlabeled 360-degree data, significantly improving accuracy.

Depth Anything V2 drastically improves monocular depth estimation by using synthetic training data, scaling up the teacher model, and employing pseudo-labeled real images. It outperforms previous met…

DEPrune: A novel GPU-optimized pruning method for depthwise separable convolutions, achieving up to 3.74x speedup on EfficientNet-B0 with no accuracy loss!

DePLM enhances protein optimization by denoising evolutionary information in protein language models via a rank-based diffusion process, improving mutation effect prediction and generalization.

GPR4DUR leverages Gaussian Process Regression to create density-based user representations for accurate multi-interest personalized retrieval, overcoming limitations of existing methods.