Algorithmic Scratchpads and Curriculum Staging for Arithmetic Reasoning in Tiny TransformersResearchOct 8, 2026
Expert Coupling in MoE Pretraining: Reducing All-to-All Overhead with Correlated Placement and Token ShufflingResearchOct 8, 2026
DSTNet: Dynamic Spectral Trajectory Network for Causal Multi-Horizon Financial ForecastingResearchOct 8, 2026
Seeing Is No Longer Believing: Frontier Image Generation Models, Synthetic Visual Evidence, and Real-World RiskResearchOct 8, 2026
APCD: Adaptive Path-Contrastive Decoding for Reliable Large Language Model GenerationResearchOct 8, 2026
Iris-3B: Going Beyond the Latent with Pixel-Space Diffusion Training, Conversion and Fine-TuningResearchOct 8, 2026
Do Image Editors Follow Depth-Dependent Blur and Aperture Response? A Rendered-Ground-Truth Pilot AuditResearchOct 8, 2026
Layerwise Error Attribution for Fast and Robust Mixed-Precision Post-Training QuantizationResearchOct 8, 2026