Recurrent Self-Improvement: Dynamic Cross-Loop On-Policy Distillation for Looped Language ModelsResearchOct 9, 2026
MESSENGER: Memory-Enhanced Sequential Scene Flow Estimation via Autoregressive Next-Frame ForecastingResearchOct 9, 2026
Enabling Preference-driven Unlearning in Few-step Distilled Text-to-Image Diffusion ModelsResearchOct 9, 2026
LinSlot: Exploiting Linear Representation hypothesis for unsupervised attribute discovery from slot based object representationResearchOct 9, 2026
OpenProblemBench: Benchmarking AI on Open Problems in the Foundational Theoretical SciencesResearchOct 9, 2026
Visible Reasoning Is Not a Universal Optimizer: Persona- and Thinking-Dependent Effects in Analytics Code GenerationResearchOct 9, 2026