DRScaffold: Boosting Dense-Scene Reasoning in Lightweight Vision Language Models

arXiv:2605.26038 · cs.CV, cs.AI · Submitted 2026-05-25 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-05-25

Updated: 2026-10-30

Terminology

• Benchmark — 3× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Vision-language models — 1× in this paper · explained in 2 episodes

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• Dreaming in Flow: Bidirectional Self-Refinement for Unified Multimodal Models
• Vorch-IR: Long-Form Unified Multimodal Identity Replacement Video Generation
• WorldMesh: Generating Navigable Multi-Room 3D Scenes via Mesh-Conditioned Image Diffusion
• OctWorld: Long-Range World-Consistent Video Generation with Octree-Based 3D Mapping
• Vorch-Streamer: Extending Human Audio-Visual Generation to Real-Time Long-Form Streaming