Perception Before Supervision: Self-Contained Visual Distillation from Counterfactual Blind Spots
- Published
- Source
- arXiv
- Paper number
- 869
- Field
- Computer Vision
- arXiv ID
- 2608.09931
Key points
- It proposes a three-stage verification criterion that finds visual blind spots using only the model's own counterfactual responses, without external models, annotations, or tools.
- It performs contrastive distillation with an expanded view of the blind spot as the positive teacher and a removed view as the negative teacher.
- On Qwen3-VL-8B, it improves all 12 benchmarks with no regression.
- It records gains of +3.60 on OCRBench, +3.38 on fine-grained perception in MMStar, and +3.08 on logical reasoning.
- It outperforms all six self-evolution baselines that depend on external GPT-4o supervision.
Paper links
External research summaries. These are not HDATF publications or measured product results.