AI Paper Atlas

Research map / Large language models / Alignment and preferences

UrbanAlign: Post-hoc Semantic Calibration for VLM-Human Preference Alignment

Yecheng Zhang, RONG ZHAO, Zhizhou Sha, Yong Li, Lei Wang, Ce Hou, Wen Ji, HUANG HAO, yunshan wan, Jian Yu, Junhao Xia, Yuru Zhang and 1 more

ECCV 2026 · Large language models › Alignment and preferences · approach: Reward model design and preference models · 1 citations (OpenAlex)

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
add LWRR calibration on top of raw Mode 4 scores (ablation)UrbanAlign · Place Pulse 2.0 (6-category avg)accuracy (%): 55.9 -> 72.2Improved
add LWRR calibration (ablation)UrbanAlign · Place Pulse 2.0 boringaccuracy (%): 38.9 -> 70.2Improved
add LWRR calibration (ablation)UrbanAlign · Place Pulse 2.0 depressingaccuracy (%): 42.9 -> 68.2Improved
add multi-agent deliberation to pairwise scoring (ablation)UrbanAlign · Place Pulse 2.0 (6-category avg)accuracy (%): 51.9 -> 72.2Improved
add multi-agent deliberation to single-image scoring (ablation)UrbanAlign · Place Pulse 2.0 (6-category avg)accuracy (%): 50.9 -> 55.9Improved
add pairwise context without multi-agent deliberation (ablation)Single-shot scoring · Place Pulse 2.0 (6-category avg)accuracy (%): 50.9 -> 51.9No clear effect
replace zero-shot holistic prompting with structured dimension scoring (raw) (ablation)GPT-4o · Place Pulse 2.0 (6-category avg)accuracy (%): 56.7 -> 55.4No clear effect
add multi-agent deliberation to structured dimension scoring (raw, no LWRR) (ablation)UrbanAlign Mode 2 · Place Pulse 2.0 (6-category avg)accuracy (%): 55.4 -> 55.9No clear effect
replace global ridge on semantic differences with local LWRR (ablation)UrbanAlign · Place Pulse 2.0 (6-category avg)accuracy (%): 61.2 -> 72.2Improved
increase neighbourhood size K_max from 10 to 20 (ablation)LWRR · Place Pulse 2.0 avg (default config)accuracy (%): 54.1 -> 58.4Improved
raise CLIP weight alpha from 0.1 to 0.3 in hybrid space (ablation)LWRR · Place Pulse 2.0 avg (default config)accuracy (%): 55.9 -> 58.4Improved
increase equal threshold epsilon from 0.3 to 2.0 (ablation)LWRR · Place Pulse 2.0 avgaccuracy (%): 60.9 -> 63.0Improved

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