Script Choice in LLMs: Evidence for Late-Layer Commitment
Research
Research News
New papers, breakthroughs and academic AI research
Benchmarking Argumentative Behaviour of LLMs: A Study of Defences Against Character Attacks
Research
Adversarial Closed-Loop Curriculum for Evolving Role-Playing Agents
Research
CinematicVQA: Benchmarking Film-Grammar Reasoning in Large Vision-Language Models
Research
Small yet Assistive: Spatially-Aware Post-Training for Low Vision
Research
DEEPO: Dual-Entropy Enhanced Policy Optimization for Hallucination in MLLMs
Research
When Should Forecasting Agents Reason? Behavioral Stress Tests for Reliability Routing
Research
RQ-Reg: A Residual-Quantization-Based Framework for Continuous Value Prediction in Recommender Systems
Research
Gradient Networks for Universal Magnetic Modeling of Synchronous Machines
Research
DrGait: Biomechanically Grounded Visual Reasoning for Interpretable Clinical Gait Analysis
Research
GeoNLI - A Natural Language Interpreter for Satellite Imagery
Research
Temporal Taxation Compounds Under Post-Training Compression of Whisper Models
Research