# SCVIB: Editable State-Conditioned Visual Instance Binding for Multi-Turn Personalized Localization

arXiv: https://arxiv.org/abs/2608.14148 · HTML: https://mlsanity.com/paper/2608.14148/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 54 references that are in the map.
- First posted on arXiv 14 Aug 2026.

## Builds on (most cited first, 5 of 5)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning](https://mlsanity.com/paper/2507.01006/) (2025)

## Abstract (arXiv)

Stored visual evidence can remain unchanged while its relevance to a current request changes with interaction state. To study this state-dependent source relevance, we introduce SCVIB, a controlled diagnostic benchmark for editable state-conditioned visual instance binding. SCVIB contains 1,050 manually verified support-query pairs and 1,500 multi-turn episodes across five visual domains and four target-state dependencies. Executable state semantics separate target resolution from evidence selection and query-side localization. Direct Qwen3-VL-8B inference achieves 99.53% target-resolution accuracy but 62.00% Joint@0.5, revealing a 37.53-point resolution-localization gap; 563 of its 570 joint failures follow correct target identification. Routing comparisons and fixed-checkpoint support interventions diagnose a post-resolution evidence-utilization bottleneck: successful resolution must be coupled with relevant visual evidence and effective query-side grounding. We introduce TT-VG (Transition-Trace Visual Grounding), a state-conditioned visual grounding framework with an explicit and auditable state-to-evidence-to-grounding path. Target-State Transition Trace (TSTT) executes editable state and selects an auditable support record; Visual Evidence Grounding Adaptation (VEGA) learns support-conditioned grounding from target appearance, boxed support context, and the query. The canonical TT-VG configuration reaches 69.80% Joint@0.5, improving over direct inference by 7.80 points at the combined evidence-utilization and grounding interface. Task adaptation improves the DINOv2 and MASA retrieval baselines to 51.47% and 55.67%, respectively, but both remain substantially below VEGA. These findings highlight state-dependent source selection and evidence utilization as consequential interfaces for interactive multimodal information fusion.