Safe Reinforcement Learning via Recovery-based Shielding with Gaussian Process Dynamics Models
Research
Research News
New papers, breakthroughs and academic AI research
Interpretability-by-Design with Accurate Locally Additive Models and Conditional Feature Effects
Research
Proof-Carrying Materials: Falsifiable Safety Certificates for Machine-Learned Interatomic Potentials
Research
DiTGaze: Geometry-Conditioned Diffusion Augmentation for Few-Shot Gaze Estimation
Research
NP-LoRA: Null Space Projection for Subject-Style LoRA Fusion
Research
Instruction-Tuning Open-Weight Language Models for BPMN Model Generation
Research
STRIATUM-CTF: A Protocol-Driven Agentic Framework for Autonomous CTF Solving
Research
DRScaffold: Boosting Dense-Scene Reasoning in Lightweight Vision Language Models
Research
MIC-BEV: Multi-Infrastructure Camera Bird's-Eye-View Transformer with Relation-Aware Fusion for 3D Object Detection
Research
Differential Vector Erasure: Unified Training-Free Concept Erasure for Flow Matching Models
Research
AdaGS: Confidence-Gated Diffusion Adaptation for Unposed Sparse-View 3D Gaussian Reconstruction
Research
MuCALD-SplitFed: Causal-Latent Diffusion for Privacy-Preserving Multi-Task Split-Federated Medical Image Segmentation
Research