安全性・評価
A
71 件中 61〜71 件目を表示
-
SEMA-Auto: Sighted and Efficient Multi-Turn Attack with Autonomy
-
Multi-Objective Reinforcement Learning Using Routed Ensembles and Trajectory Attribution
-
The Watchtower Imperative: Lifespan-Calibrated Evaluation for Frontier AI
-
OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images
-
Evaluating DeepSeek V4.1 Flash-1017 for loss of control and harmful manipulation risks
-
A Hybrid Framework for Explainable Aviation Risk: Causal Chain Extraction from Safety Reports with Physics-Based Failure Quantification and Interventional Analysis
-
From Language to Drives: A Multimodal Framework for Aligning Autonomous Robots with Human Purposes
-
Distributed Predictive Flocking for a Swarm of Miniature Vibration-Driven Robots in a Confined Arena
-
Beyond Modeling Order: Dual-Path Spatiotemporal Representation Learning for Cross-Subject EEG Emotion Recognition
-
CANS: Capability-Preserving Neuron Steering for Large Language Models
-
Probing the phon* representations of the Mimi codebooks