Decentralized SGD under Heavy-Tailed Noise: Optimal Convergence Rates and the Role of Gradient Clipping
Research
Research News
New papers, breakthroughs and academic AI research
The Utility and Complexity of in- and out-of-Distribution Machine Unlearning
Research
Causal Posterior Estimation
Research
Modified Loss of Momentum Gradient Descent: Fine-Grained Analysis
Research
SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
Research
HomID : Benchmarking Intrinsic Dimension Estimators on Homogenous Manifolds with Anisotropic Embeddings
Research
Estimating Model-Level Membership Inference Vulnerability Without Reference Models
Research
PrismSSL: One Interface, Many Modalities; A Single-Interface Library for Multimodal Self-Supervised Learning
Research
DiTS: Multimodal Diffusion Transformers Are Time Series Forecasters
Research
ELROND: Exploring and decomposing intrinsic capabilities of diffusion models
Research
Correspondences as Decisions: JevNexus for Decision-Centric Schema Matching
Research
PARC-Loc: Text-to-Point-Cloud Localization with Partial Assignment and Relational Consistency
Research