🏢 Wuhan University

Boost OOD detection accuracy by averaging model confidence scores from original and corrupted inputs!

SGNet cultivates general segmentation models for ultra images by integrating surrounding context, achieving significant performance improvements across various datasets.

OKRidge’s reliability for solving sparse ridge regression problems is rigorously proven through theoretical error analysis, enhancing its applicability in machine learning.

Text-DiFuse: A novel interactive multi-modal image fusion framework leverages text-modulated diffusion models for superior performance in complex scenarios.

ROBIN: A novel watermarking method for diffusion models that actively conceals robust watermarks using adversarial optimization, enabling strong, imperceptible, and verifiable image authentication.

Reference Trustable Decoding (RTD) revolutionizes large language model adaptation by offering a training-free method, enabling efficient and cost-effective task adaptation without parameter adjustment…

Prospective Representation Learning (PRL) revolutionizes non-exemplar class-incremental learning by proactively reserving embedding space for new classes and minimizing the shock of new data on previo…

FDCR defends against backdoor attacks in heterogeneous federated learning by identifying malicious clients via Fisher Information-based parameter importance discrepancies and rescaling crucial paramet…

New non-asymptotic approximation error bounds show that parameterized quantum circuits can efficiently approximate complex functions, potentially surpassing classical neural networks.

InfoRM tackles reward hacking in RLHF using an information-theoretic approach, enhancing generalizability and enabling overoptimization detection.

FedSSP tackles personalized federated graph learning challenges by sharing generic spectral knowledge and incorporating personalized preferences, achieving superior performance in cross-domain scenari…

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.

Solved a long-standing open problem: Factorized ADABOOST.MH now has a proven convergence rate!