Spatial-OPSD: Self-Improving Spatial Reasoning via Label-Free Self-Distillation

arXiv:2609.37055 · cs.CV · Submitted 2026-09-29 · Read on arXiv

cs.CV

Submitted: 2026-09-29

Updated: 2026-09-29

Code: https://github.com/vermouth599/Spatial-OPSD

Terminology

• Distillation — 28× in this paper · explained in 2 episodes
• Benchmark — 19× in this paper · explained in 2 episodes
• Self-Distillation — 12× in this paper · explained in 7 episodes
• GRPO — 7× in this paper · explained in 6 episodes
• On-Policy Distillation — 6× in this paper · explained in 3 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Accuracy — 5× in this paper · explained in 1 episode
• Grounding — 5× in this paper · explained in 3 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Vision-Language Models (VLMs) — 2× in this paper · explained in 6 episodes
• Activation Checkpointing — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Information Asymmetry — 1× in this paper · explained in 2 episodes
• Knowledge Distillation — 1× in this paper · explained in 11 episodes
• LoRA Adapters — 1× in this paper · explained in 3 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Point Clouds — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Thinking mode — 1× in this paper · explained in 2 episodes

Sources

• On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes
• LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training
• Qwen3-VL Technical Report
• Scaling Spatial Intelligence with Multimodal Foundation Models
• SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities
• Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views
• SIFThinker: Spatially-Aware Image Focus for Visual Reasoning
• 4DThinker: Thinking with 4D Imagery for Dynamic Spatial Understanding
• Emerging Properties in Unified Multimodal Pretraining
• Gemma 3 Technical Report
• MiniLLM: On-Policy Distillation of Large Language Models
• Reinforcement Learning via Self-Distillation
• ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models
• Video-OPD: Efficient Post-Training of Multimodal Large Language Models for Temporal Video Grounding via On-Policy Distillation
• Visual-Advantage On-Policy Distillation for Vision-Language Models
• Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection
• 3DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark
• SAM 2: Segment Anything in Images and Videos
• Self-Boosting Vision-Language Models with Noisy Student On-Policy Self-Distillation
• InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models