Blocking at the Boundary: Auditing Long-Horizon Agents against Staged Prompt Injection
Research
Research News
New papers, breakthroughs and academic AI research
Hidden Risks of Jev: An Empirical Study of Security, Privacy, and Dual Use
Research
Same Predictions, Different Harms: Causal Auditing of Patient World Models
Research
Settling the Computational Complexity of Max-Min Allocation with Ternary Valuations
Research
Vela: Scaling Vision-Language-Action Models with Adaptive Action Curve Parametrization
Research
Who Is Your Agent Serving? Provider-Side Indirect Prompt Injection in Proactive Agents
Research
Lightweight Semantic EEG Foundation Model for Frozen Cross-Disorder Transfer
Research
LiFT: Loop Flow Transformers
Research
Cut Binary Cross Entropy: Efficient Large-Vocabulary Loss and Gradient Kernels for Sequential Recommendation
Research
Keepsake: Selective Spatial Memory for Long-Horizon Video Generation
Research
VAMPS: Visual and Motor Policies from Sampling-Based Planning
Research
Human-Like Attention? A Psychophysical Comparison of Visual Search in Humans and MLLMs
Research