Posters

New Perturbation Gradient losses connect expected decisions with directional derivatives, enabling Lipschitz continuous surrogates for predict-then-optimize, asymptotically yielding best-in-class poli…

Decision Mamba-Hybrid (DM-H) accelerates in-context RL for long-term tasks by cleverly combining the strengths of Mamba’s linear long-term memory processing and transformer’s high-quality predictions,…

Decision Mamba: a novel offline RL model, leverages a multi-grained state space model and self-evolution regularization to overcome challenges with out-of-distribution data and noisy labels, achieving…

Decentralized noncooperative games with coupled decision-dependent distributions are analyzed, providing novel equilibrium concepts, uniqueness conditions, and a decentralized algorithm with sublinear…

Debiasing synthetic data generated by deep generative models enhances statistical convergence rates, yielding reliable results for specific analyses.

DeBaRA: a novel denoising-based model generates realistic & controllable 3D room layouts, surpassing existing methods.

AI-generated images contaminate online continual learning datasets, hindering performance. A new method, ESRM, leverages entropy and real/synthetic similarity maximization to select high-quality data…

Deep Degradation Response (DDR) uses image deep feature changes under degradation to create a flexible image descriptor, excelling in blind image quality assessment and unsupervised image restoration.

DDN: Dual-domain Dynamic Normalization dynamically improves time series forecasting accuracy by addressing data distribution changes in both time and frequency domains via a plug-in module.

DDK: Dynamically Distilling Domain Knowledge for efficient LLMs.

DDGS-CT: A novel direction-disentangled Gaussian splatting method creates realistic X-ray images from CT scans, boosting accuracy and speed for applications such as image-guided surgery and radiothera…

DCDepth achieves state-of-the-art monocular depth estimation by progressively predicting depth in the frequency domain via DCT, capturing local correlations and global context effectively.

DC-Gaussian: A novel method generates high-fidelity novel views from dashcam videos by addressing common windshield obstructions (reflections, occlusions) using adaptive image decomposition, illumina…

Attackers can steal massive private data from federated learning diffusion models using multiple Trojans and an advanced attack, AdaSCP, which circumvents existing defenses.

This paper introduces dataset decomposition (DD), a novel approach to accelerate LLM training while enhancing performance. DD significantly reduces training time by decomposing datasets into buckets …

Data-faithful feature attribution tackles misinterpretations from unobservable confounders by using instrumental variables to train confounder-free models, leading to more robust and accurate feature …

Data-efficient neural operator learning is achieved via unsupervised pretraining and in-context learning, significantly reducing simulation costs and improving generalization.

ISED: a novel, data-efficient algorithm learns neural programs by sampling from neural predictions to estimate gradients of black-box components, outperforming baselines on various benchmarks.

LLMs iteratively discover and refine interpretable dynamical systems models, achieving high accuracy and uncovering new insights; demonstrated by a novel Warfarin model.

Sublinear coresets for Poisson regression are developed, offering 1±ε approximation guarantees, with complexity analyzed using a novel parameter and domain shifting.