They Can See It but Not Say It: Iterative Self Knowledge Re-expression in Visual Reasoning Relative Pose Identification
cs.CV
Submitted: 2026-11-07
Updated: 2026-11-07
Code: https://github.com/astudentuser/Codes_of_SKR-ID
Terminology
Sources
- Qwen3-VL Technical Report
- Lost in Space? Vision-Language Models Struggle with Relative Camera Pose Estimation
- Spatial-DISE: A Unified Benchmark for Evaluating Spatial Reasoning in Vision-Language Models
- Spa3R: Predictive Spatial Field Modeling for 3D Visual Reasoning
- Linear Mechanisms for Spatiotemporal Reasoning in Vision Language Models
- ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models
- Isambard-AI: a leadership class supercomputer optimised specifically for Artificial Intelligence
- Loc3R-VLM: Language-based Localization and 3D Reasoning with Vision-Language Models
- Epipolar-Constrained Graph Representation Learning for Geometric Pose Estimation
- Self Knowledge Re-expression: A Fully Local Method for Adapting LLMs to Tasks Using Intrinsic Knowledge
- Fine-tuning Pre-trained Vision-Language Models in a Human-Annotation-Free Manner
- Visual Spatial Tuning
- MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence
- A Progressive Training Strategy for Embodied Vision-Language Models to Mitigate Spatio-Temporal Hallucinations
- SpatialStack: Layered Geometry-Language Fusion for 3D VLM Spatial Reasoning
- Predicting Camera Pose from Perspective Descriptions for Spatial Reasoning
- ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs