🏢 Xi'an Jiaotong University

Topology-Preserving Reservoirs (TPR) enhances CLIP’s zero-shot learning by using a dual-space alignment and a topology-preserving objective to improve generalization to unseen classes, achieving state…

Prompt-Agnostic Adversarial Perturbation (PAP) defends customized diffusion models against image tampering, achieving superior generalization over prompt-specific methods.

OneActor: One-shot tuning for consistent subject image generation, bypassing laborious backbone tuning via semantic guidance, achieving 4x faster speed.

Neural P³M enhances geometric GNNs by incorporating mesh points to model long-range interactions in molecules, achieving state-of-the-art accuracy in predicting energy and forces.

MADPO, a novel MARL framework, uses mutual policy divergence maximization with conditional Cauchy-Schwarz divergence to enhance exploration and agent heterogeneity in sequential updating, outperformin…

New dataset MUSIC-AVQA-R and a multi-faceted cycle collaborative debiasing strategy significantly improve audio-visual question answering robustness.

3D surface reconstruction revolutionized: PEIF leverages patch-level pose-invariant representations and 3D patch-level equivariance for state-of-the-art accuracy, even with varied poses and datasets!

IPM-LSTM accelerates nonlinear program solving by up to 70% using LSTM networks to approximate linear system solutions within the interior point method.

FlipClass dynamically updates the teacher model in a teacher-student framework to align with the student’s attention, resolving learning inconsistencies and significantly improving generalized categor…

Boost language model performance across domains with ‘Concentration’: a new prompt optimization objective that prioritizes stable, deep-layer attention.

ColJailBreak cleverly circumvents AI safety filters by first generating safe images and then subtly injecting unsafe content using image editing.