Large language models exhibit unreliable updating of clinical judgment as patient evidence evolves
Research
Research News
New papers, breakthroughs and academic AI research
Correcting Guided Diffusion Trajectories with Spectral Alignment
Research
Designing the Future of User Feedback for Generative AI
Research
TerrainForge: Physics-Grounded road geometry Editing for Counterfactual Autonomous Driving
Research
A GHOST in Long-Horizon Agents: Governance Hazard from Overlooked Safety Constraints across Turns
Research
Decoupling Memory from Context: Structured Memory for Token-Efficient Test-Time Continual Learning
Research
Mitigating Convergence Collapse in Fixed-Target Anomaly Detectors via Kernel-Anchored Locality Regularization
Research
ArrivalBench: Agent-Generated Data Pipelines Are Correct Once and Wrong Under Time
Research
CuBEs: Culturally-Situated Behavioral Evaluations and the Limitations of Culture-Blind LLM Judges
Research
Lost in the Request: How Communication Variation Disrupts Retrieval and Action in Email Agents
Research
FUSEye: Training-Light Fisheye Detection with Overlapping Views and Zero-Initialized Adapters
Research
Output Language Confusion under Multilingual Prompt Contamination
Research