SpanVLA: Learning from Negative-Recovery Samples with Fast Action Bridging for Vision-Language-Action Model
Research
Research News
New papers, breakthroughs and academic AI research
A method for multimodal analysis of TAIGA experiment data using essential features
Research
Empirical Evidence for Simply Connected Decision Regions in Image Classifiers
Research
Quadratic Weak-to-Strong Generalization in Random Feature Networks via Random Matrix Theory
Research
Dual-Pathway Circuits of Object Hallucination in Vision-Language Models
Research
Learning Transition Kernels of Jump-Diffusion Processes with Conditional Diffusion Models
Research
Open-CHOIR: Open-World Contact-Aware 4D Hand-Object Interaction Reconstruction
Research
Hand-4DGS: Feed-Forward 3D Gaussian Splatting for 4D Hand Reconstruction from Egocentric Videos
Research
Hidden in Plain Sight: Benchmarking Agent Safety Against Decomposition Attacks with DECOMPBENCH
Research
SWE-NFI: Studying and Benchmarking Coding Agents for Non-Functional Improvements
Research
Covariate-dependent Joint Modeling of Multivariate Ordinal Preferences and Its Connections with Comparison Models
Research
ArapaiSecure: An Autonomous AI Security Agent for Banking: Multi-Vector Fraud and AML Detection Across Retail and Corporate Accounts
Research