<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-wang-2026-cityvg">
    <titleInfo>
        <title>CityVG: Contrastive Fine-Tuning and Reward-Based Chain-of-Thought Reasoning for Zero-Shot City-Scale 3D Visual Grounding</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jianjun</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hanli</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Liakata</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Viviane</namePart>
            <namePart type="given">P</namePart>
            <namePart type="family">Moreira</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jiajun</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Jurgens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-390-6</identifier>
    </relatedItem>
    <abstract>3D Visual Grounding (3DVG) locates objects in 3D scenes based on natural language descriptions. However, existing methods are primarily confined to small-scale indoor data or rely on heavy supervision, failing to generalize to the complexity of large-scale urban environments. To address this limitation, we present CityVG, the first city-scale zero-shot 3D visual grounding framework capable of localizing urban objects without manual annotations. Our approach adopts a retrieval-and-reasoning paradigm comprising two key components. Specifically, we propose a contrastive fine-tuning strategy to align textual queries with urban scene graphs. By leveraging an LLM-driven graph clustering mechanism, we automatically construct high-quality positive and negative training pairs and fine-tune the text encoder via contrastive learning, resulting in a scene-adaptive text encoder that enables efficient alignment without grounding supervision. Complementing this, we introduce a multi-trajectory reward-based Chain-of-Thought (CoT) reasoning strategy for inference. This mechanism iteratively evaluates candidate objects by aggregating reward scores across diverse reasoning trajectories, selecting the target that is most consistent with both appearance and spatial constraints. Extensive experiments on city-scale 3D grounding benchmarks demonstrate that CityVG achieves strong zero-shot localization performance and generalizes effectively to unseen urban environments.</abstract>
    <identifier type="citekey">zhang-wang-2026-cityvg</identifier>
    <identifier type="doi">10.18653/v1/2026.acl-long.1617</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-long.1617/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>35012</start>
            <end>35031</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T CityVG: Contrastive Fine-Tuning and Reward-Based Chain-of-Thought Reasoning for Zero-Shot City-Scale 3D Visual Grounding
%A Zhang, Jianjun
%A Wang, Hanli
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F zhang-wang-2026-cityvg
%X 3D Visual Grounding (3DVG) locates objects in 3D scenes based on natural language descriptions. However, existing methods are primarily confined to small-scale indoor data or rely on heavy supervision, failing to generalize to the complexity of large-scale urban environments. To address this limitation, we present CityVG, the first city-scale zero-shot 3D visual grounding framework capable of localizing urban objects without manual annotations. Our approach adopts a retrieval-and-reasoning paradigm comprising two key components. Specifically, we propose a contrastive fine-tuning strategy to align textual queries with urban scene graphs. By leveraging an LLM-driven graph clustering mechanism, we automatically construct high-quality positive and negative training pairs and fine-tune the text encoder via contrastive learning, resulting in a scene-adaptive text encoder that enables efficient alignment without grounding supervision. Complementing this, we introduce a multi-trajectory reward-based Chain-of-Thought (CoT) reasoning strategy for inference. This mechanism iteratively evaluates candidate objects by aggregating reward scores across diverse reasoning trajectories, selecting the target that is most consistent with both appearance and spatial constraints. Extensive experiments on city-scale 3D grounding benchmarks demonstrate that CityVG achieves strong zero-shot localization performance and generalizes effectively to unseen urban environments.
%R 10.18653/v1/2026.acl-long.1617
%U https://aclanthology.org/2026.acl-long.1617/
%U https://doi.org/10.18653/v1/2026.acl-long.1617
%P 35012-35031

Markdown (Informal)

[CityVG: Contrastive Fine-Tuning and Reward-Based Chain-of-Thought Reasoning for Zero-Shot City-Scale 3D Visual Grounding](https://aclanthology.org/2026.acl-long.1617/) (Zhang & Wang, ACL 2026)

• CityVG: Contrastive Fine-Tuning and Reward-Based Chain-of-Thought Reasoning for Zero-Shot City-Scale 3D Visual Grounding (Zhang & Wang, ACL 2026)

ACL

• Jianjun Zhang and Hanli Wang. 2026. CityVG: Contrastive Fine-Tuning and Reward-Based Chain-of-Thought Reasoning for Zero-Shot City-Scale 3D Visual Grounding. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 35012–35031, San Diego, California, United States. Association for Computational Linguistics.