WinARDet: Compressed Window Auto-Regression for Long-Horizon Vision-Language Grounding
arXiv:2610.19419v1 Announce Type: new Abstract: MLLM-based detectors formulate vision-language grounding as autoregressive coordinate generation, yet in dense scenes, they often collapse into a box repetition loop, repeatedly emitting identical boxes until the decoding budget is exhausted. We trace…
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-10-15 04:00 · arXiv cs.CV
WinARDet: Compressed Window Auto-Regression for Long-Horizon Vision-Language Grounding