Where Does Proposal Selection Fail? Diagnosing Frozen Vision-Language Queries over Detector Proposals
cs.CV
Submitted: 2026-11-09
Updated: 2026-11-09
Terminology
Sources
- Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic
- RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension
- GREC: Generalized Referring Expression Comprehension
- ChatRex: Taming Multimodal LLM for Joint Perception and Understanding
- Zero-Shot Referring Expression Comprehension via Vison-Language True/False Verification
- VLM-FO1: Bridging the Gap Between High-Level Reasoning and Fine-Grained Perception in VLMs
- HKVLM: Faithful Query--Region Binding for Frozen-Detector Visual Grounding
- PROVE: Probabilistic Visual Grounding via Patch-Level Evidence for Vision-Language Models
- DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding
- Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection
- FORUM: Frozen Outputs Reconciled Using Model Agreement for Visual Grounding
- LOCUS: Locate Once, Check Until Settled. Draft-and-Verify Visual Grounding with a Box Head and Coordinate-Token Verification
- Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
- Towards Open-World Referring Expression Comprehension: A Benchmark with Training-free Multi-task Consistency Checker
- Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
- Teaching MLLMs to Say No: Generalized Referring Expression Comprehension via Refusal Calibrated GRPO
- Griffon-G: Bridging Vision-Language and Vision-Centric Tasks via Large Multimodal Models
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