From Latents to Wires: Surgical Post-Editing on Large Language Models
Research
Research News
New papers, breakthroughs and academic AI research
Masking Frequent Tokens Sharpens Direct Preference Optimization
Research
Mandela-Bench: Multimodal Models Remember Canonical Images Instead of Seeing Them
Research
Attribution Gaps in Zero-Training LLM+OVOD Pipelines: A Fine-Grained Analysis of the CAAP--SNAP Discrepancy
Research
Can Circuit Alignment Predict OOD Generalization?
Research
Fusion Under Component Failure: Negative Results and Failure Modes in Ensemble AI-Generated Image Detection
Research
VisionPsy-Nano: Improving Accuracy, Efficiency, and Reliability in On-Device Vision-Language Models
Research
Controllable GNN Explanations via Multi-Metric Preference Selection
Research
PC-SubMax: Efficient Prompt Compression via Regularized Submodular Maximization
Research
MA-FPPO: Multi-Agent Flow-Pretrained Policy Optimization
Research
Multi-Agent System Search via Active Substructure-aware Policy Optimization
Research
Fisher Simplicity in Kolmogorov-Arnold Networks and Multilayer Perceptrons
Research