Posters

Dual-Perspective Activation (DPA) efficiently denoises ANN channels by jointly using forward and backward propagation criteria, improving sparsity and accuracy.

Federated Dual-Personalizing Adapter (FedDPA) tackles test-time distribution shifts and personalization in federated foundation models using a global and local adapter co-working mechanism, achieving …

Self-supervised dual-frame fluid motion estimation achieves superior accuracy with 99% less training data, using a novel zero-divergence loss and dynamic velocimetry enhancement.

Dual-Diffusion boosts binocular 3D human pose estimation accuracy by simultaneously denoising 2D and 3D pose uncertainties using a diffusion model.

Dual Risk Minimization (DRM) improves fine-tuned zero-shot models’ robustness by combining empirical and worst-case risk minimization, using LLMs to identify core features, achieving state-of-the-art …

Dual Prototype Evolving (DPE) significantly boosts vision-language model generalization by cumulatively learning multi-modal prototypes from unlabeled test data, outperforming current state-of-the-art…

Dual Lagrangian Learning (DLL) revolutionizes conic optimization by leveraging machine learning to efficiently learn high-quality dual-feasible solutions, achieving 1000x speedups over traditional sol…

Dual encoder GAN inversion achieves high-fidelity 3D head reconstruction from single images by cleverly combining outputs from encoders specialized for visible and invisible regions, surpassing existi…

Dual Defense Federated Learning (DDFed) simultaneously boosts privacy and thwarts poisoning attacks in federated learning without altering the existing framework.

DCRL, a Dual Critic Reinforcement Learning framework, effectively mitigates high variance in reinforcement learning under partial observability by synergistically combining an oracle critic (with full…

Dual Cone Gradient Descent (DCGD) enhances Physics-Informed Neural Network (PINN) training by resolving gradient imbalance issues, leading to more accurate and stable solutions for complex partial dif…

DU-Shapley efficiently estimates the Shapley value for dataset valuation, enabling fair compensation in collaborative machine learning by leveraging the problem’s structure for faster computation.

Du-IN: Revolutionizing speech decoding from intracranial neural signals with discrete units-guided mask modeling, achieving state-of-the-art performance on a challenging Chinese word-reading sEEG dat…

SGA: A novel framework boosts Signed Graph Neural Network performance by addressing graph sparsity and unbalanced triangles, achieving up to 26.2% F1-micro improvement.

DropBP: Accelerate LLM fine-tuning by 44% while preserving accuracy!

DRIP: A novel image matting method using pre-trained latent diffusion models achieves state-of-the-art performance by jointly predicting foreground and alpha values, significantly improving accuracy a…

Drift-Resilient TabPFN masters temporal data shifts!

DreamSteerer enhances source image-conditioned editability in personalized diffusion models via a novel Editability Driven Score Distillation objective and mode shifting regularization, achieving sign…

DreamScene4D generates realistic 3D dynamic multi-object scenes from monocular videos via novel view synthesis, addressing limitations of existing methods with a novel decompose-recompose approach.

DreamMesh4D: Generating high-fidelity dynamic 3D meshes from monocular video using a novel Gaussian-mesh hybrid representation and adaptive hybrid skinning.