Gradients for Interventions and Activations for Detection: Targeted Feature Learning in Language ModelsResearchSep 29, 2026
PlurVA-LLM-2026 Shared Task Track-1: Pluralistic Value Alignment in LLMs via Multilingual Fine-Tuning and Threshold CalibrationResearchSep 29, 2026
SinBrief: A Hybrid Framework for Abstractive Text Summarisation of Sinhala Legal DocumentsResearchSep 29, 2026
Artificial intelligences and human scientists exhibit complementary strengths in theory buildingResearchSep 29, 2026
Beyond Scripted Search: Sample-Efficient Reward Discovery via Agentic Black-box OptimizationResearchSep 29, 2026
Understanding the Subspace Stabilization of the Hessian and Gradient Covariance MatrixResearchSep 29, 2026
Seeing the Heat: Synthesizing High-Resolution Wood Thermal Responses from Optical ImageryResearchSep 29, 2026