A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Lingjuan Lyu, Han Yu, Xingjun Ma, et al.
A comprehensive survey of privacy and robustness in federated learning, covering threat models, privacy attacks and defenses, and poisoning attacks and defenses over the past five years.
John N. Wright, A. Yang, Arvind Ganesh, et al.
This paper casts face recognition as classification among linear regression models and uses sparse representation via l1-minimization to achieve robustness to occlusion and disguise.
Unknown
Cultivar is a contrastive, locale-oriented translation benchmark that enables diagnosing benchmark contamination and quantifying true localisation robustness.
Unknown
The paper evaluates the robustness of in-context learning to template selection across models on classification tasks, highlighting the need for consistent evaluation.
Unknown
A survey examining trustworthiness challenges in retrieval-augmented generation for large language models, covering evaluation, robustness, and open problems.
Unknown
The paper investigates whether quality-diversity archive coverage can certify the robustness of process reward models under stress tests, finding that coverage alone is insufficient.
Unknown
Introduces PRM BiasBench, a benchmark suite for systematically evaluating the robustness and failure modes of process reward models.
Dhruva Karkada, D. Korchinski, A. Nava, et al.
This paper proves that translation symmetries in language statistics explain the geometric structures (circles, manifolds) in LLM word embeddings, deriving manifold geometry analytically and showing robustness to perturbations.
Asaf Yehudai, Lilach Eden, Alan Li, et al.
First comprehensive survey of evaluation methods for LLM-based agents, analyzing five perspectives and identifying gaps in cost-efficiency, safety, and robustness.
Unknown
Applying self-supervised learning to improve robustness and uncertainty of deep learning models beyond purely supervised methods.
Unknown
This paper introduces M-RewardBench, a benchmark for evaluating reward models in multilingual settings, revealing that current reward models exhibit limited robustness across languages.
Unknown
GaussianPro introduces progressive propagation to improve 3D Gaussian Splatting's rendering quality and robustness when initial point clouds are sparse or incomplete.