Breaking the Mirror: Activation-Based Mitigation of Self-Preference in LLM Evaluators
Research
Research News
New papers, breakthroughs and academic AI research
Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)
Research
Can phenotypic activity be predicted without experimental readouts?
Research
Detecting a Shift Is Not Enough: Exact Minimax Limits of Linear Representation Repair
Research
Common Corpus: The Largest Collection of Ethical Data for LLM Pre-Training
Research
SepsisLens: Structure-Preserving Sequence Modelling for Decomposable Early Sepsis Warning
Research
ROMA: LLM System for Real-World Object-Centric Multi-Sensory Active Perception
Research
OpenSplatGraph: From Dense Semantic Maps to Structured Scene Graphs for Open-Vocabulary Robot Perception
Research
A Riemannian Geometry for Low-rank Adaptation
Research
Emoception: Selective Affective Layer Fine-Tuning of Video Vision Transformers for Player Arousal Change Recognition From Gameplay Footage
Research
VietBinoculars: A Zero-Shot Approach for Detecting Vietnamese LLM-Generated Text
Research
Monocular Navigation Relative to Unknown Spacecraft Using a Transformer-Aided Kalman Filter
Research