On the Faithfulness of Visual Thinking: Measurement and Enhancement

arXiv:2510.23482 · cs.CV, cs.AI · Submitted 2025-10-27 · Read on arXiv

cs.CV, cs.AI

Submitted: 2025-10-27

Updated: 2026-10-30

Terminology

• Faithfulness — 5× in this paper · explained in 2 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Sufficiency — 1× in this paper · explained in 2 episodes
• Sufficient-Component Cause Model — 1× in this paper
• 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