Restricting the Model, Missing the System: Measurement and Accountability in Offensive AI Governance
Research
Research News
New papers, breakthroughs and academic AI research
EasyLens: A Training-Free Plug-and-Play Subtle-Lesion Representation Amplifier for Medical Vision-Language Models
Research
Targeting World Models to Compromise Robot Learning Pipelines
Research
Cross-Agent Learning Signals Enable Coordinated Role-Decomposed LLM Training
Research
Component-Adaptive and Lesion-Level Supervision for Improved Small Structure Segmentation in Brain MRI
Research
A Few Steps Further: Why Defenses Against Malicious Finetuning Erode Under Continued Training
Research
Residualized Temporal Sparse Autoencoders for Interpreting Diffusion Models
Research
Task-Sufficient Contraction: Source Selection for Machine Information Interfaces
Research
FiRe: Fine-grained Multimodal Reasoning for Enhanced Image Generation
Research
HULK: Learning Whole-Body Forceful Loco-Manipulation for Humanoids
Research
Geological text descriptions in ill-posed inverse problems: insights from learned hydraulic-conductivity inversion
Research
VIA: Visual Interface Agent for Robot Control
Research