AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding

Shihao Wang, Shilong Liu, Yuanguo Kuang, Xinyu Wei, Yangzhou Liu, Zhiqi Li, Yunze Man, Guo Chen, Andrew Tao, Guilin Liu, Jan Kautz, Lei Zhang and 1 more

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Attention-based visual token pruning

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use box-aligned parallel box decoding (Slow mode) instead of quantized coordinate tokens (ablation)LocateAnything-3B · COCO ablationF1: 50.1 -> 52.1Improved
use quantized coordinate tokens instead of textual digits (ablation)NTP baseline · COCO ablationF1: 49.1 -> 50.1Improved
switch from Slow (NTP) to Fast (MTP) decoding (ablation)LocateAnything-3B · COCO ablationF1 and throughput: 52.1 -> 49.6 F1, 3.9 -> 16.9 BPSMixed
add hybrid NTP fallback on top of Fast mode (ablation)LocateAnything-3B · COCO ablationF1 and throughput: 49.6 -> 51.6 F1, 16.9 -> 13.2 BPSImproved
add joint NTP and block losses instead of NTP loss only (Slow mode) (ablation)LocateAnything-3B · COCO ablationF1: 50.1 -> 52.1Improved
add NTP loss to block-loss-only training (Fast mode) (ablation)LocateAnything-3B · COCO ablationF1: 47.2 -> 49.6Improved
replace generic block MTP (SDLM-B6) with box-aligned PBD (ablation)MTP formulation · COCO ablationF1 and throughput: 46.1 -> 49.6 F1, 5.5 -> 16.9 BPSImproved
increase generic MTP block size from 4 to 8 (SDLM) (ablation)SDLM · COCO ablationF1 and throughput: 46.5 -> 45.8 F1, 5.2 -> 6.7 BPSHurt
order boxes by top-left distance instead of center, area or random (ablation)LocateAnything-3B · COCO ablationF1Improved
use parallel box decoding instead of NTP when target boxes grow from 20 to 300LocateAnything-3B · Throughput vs box countthroughput: 12 BPS to nearly 25 BPSImproved
train LocateAnything on 138M-query data with PBD versus Rex-OmniLocateAnything-3B · LVIS (zero-shot)mean F1: 46.9 -> 50.7Improved
LocateAnything-3B versus Rex-Omni-3B on Dense200 and VisDroneLocateAnything-3B · VisDronemean F1: 35.8 -> 39.9Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy