GeoPair: Geometry-Preserving Cross-Layer Factorization for Training-Free Transformer Compression
1
Neural Spectral Capacity: Measuring and Designing Architectures from Network Specification Alone
Refinement Is Inherently Editable: Training-Free Prompt-to-Prompt Image Editing with Generative Refinement Network
Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents
HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness
Reflection-aware Generative Novel View Synthesis
One Editor, Many Edits: A Unified Training-Free Framework for Diverse Video Editing
