Grounding language in the physical world requires AI systems to interpret references that emerge dynamically during conversation. While current vision-language models (VLMs) excel at static image tasks, they struggle to resolve ambiguous expressions in spontaneous, multi-turn dialogue. We address this gap by introducing (1) a benchmark for referential communication in dynamic 3D environments, built from 6.7 hours of egocentric VR interaction with synchronized speech, motion, gaze, and 3D scene geometry, and (2) a two-stage grounding pipeline that explicitly resolves conversational ambiguity before visual localization. The benchmark includes over 4,200 manually verified referring expressions spanning full, partitive, and pronominal types. Our contextual rewriting approach improves grounding performance by 11-22 percentage points on average, with a pure detector (GroundingDINO) reaching 56.7% on pronominals after rewriting, nearly double the best end-to-end baseline. Results demonstrate that decoupling linguistic reasoning from visual perception is more effective than end-to-end approaches for conversational grounding.
Tianjin University（天津大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））
Conventional phrase grounding aims to localize noun phrases mentioned in a given caption to their corresponding image regions, which has achieved great success recently. Apparently, sole noun phrase grounding is not enough for cross-modal visual language understanding. Here we extend the task by considering pronouns as well. First, we construct a dataset of phrase grounding with both noun phrases and pronouns to image regions. Based on the dataset, we test the performance of phrase grounding by using a state-of-the-art literature model of this line. Then, we enhance the baseline grounding mode…
Visual dialogue is a challenging task since it needs to answer a series of coherent questions on the basis of understanding the visual environment. Previous studies focus on the implicit exploration of multimodal co-reference by implicitly attending to spatial image features or object-level image features but neglect the importance of locating the objects explicitly in the visual content, which is associated with entities in the textual content. Therefore, in this paper we propose a {\bf M}ultimodal {\bf I}ncremental {\bf T}ransformer with {\bf V}isual {\bf G}rounding, named MITVG, which consi…
Decoding strategies play a crucial role in natural language generation systems. They are usually designed and evaluated in open-ended text-only tasks, and it is not clear how different strategies handle the numerous challenges that goal-oriented multimodal systems face (such as grounding and informativeness). To answer this question, we compare a wide variety of different decoding strategies and hyper-parameter configurations in a Visual Dialogue referential game. Although none of them successfully balance lexical richness, accuracy in the task, and visual grounding, our in-depth analysis allo…
The University of Tokyo（东京大学）；National Institute of Informatics（国立信息学研究所）
Common grounding is the process of creating, repairing and updating mutual understandings, which is a critical aspect of sophisticated human communication. However, traditional dialogue systems have limited capability of establishing common ground, and we also lack task formulations which introduce natural difficulty in terms of common grounding while enabling easy evaluation and analysis of complex models. In this paper, we propose a minimal dialogue task which requires advanced skills of common grounding under continuous and partially-observable context. Based on this task formulation, we co…
Data-driven, knowledge-grounded neural conversation models are capable of generating more informative responses. However, these models have not yet demonstrated that they can zero-shot adapt to updated, unseen knowledge graphs. This paper proposes a new task about how to apply dynamic knowledge graphs in neural conversation model and presents a novel TV series conversation corpus (DyKgChat) for the task. Our new task and corpus aids in understanding the influence of dynamic knowledge graphs on responses generation. Also, we propose a preliminary model that selects an output from two networks a…
Bielefeld University（比勒费尔德大学）；University of Potsdam（波茨坦大学）
Building computer systems that can converse about their visual environment is one of the oldest concerns of research in Artificial Intelligence and Computational Linguistics (see, for example, Winograd's 1972 SHRDLU system). Only recently, however, have methods from computer vision and natural language processing become powerful enough to make this vision seem more attainable. Pushed especially by developments in computer vision, many data sets and collection environments have recently been published that bring together verbal interaction and visual processing. Here, we argue that these datase…
MILA, Université de Montréal（蒙特利尔大学MILA）；Georgia Institute of Technology（佐治亚理工学院）；Facebook AI Research（Facebook人工智能研究院）
We introduce "Talk The Walk", the first large-scale dialogue dataset grounded in action and perception. The task involves two agents (a "guide" and a "tourist") that communicate via natural language in order to achieve a common goal: having the tourist navigate to a given target location. The task and dataset, which are described in detail, are challenging and their full solution is an open problem that we pose to the community. We (i) focus on the task of tourist localization and develop the novel Masked Attention for Spatial Convolutions (MASC) mechanism that allows for grounding tourist utt…
Beijing University of Posts and Telecommunications（北京邮电大学）
The Guesser is a task of visual grounding in GuessWhat?! like visual dialogue. It locates the target object in an image supposed by an Oracle oneself over a question-answer based dialogue between a Questioner and the Oracle. Most existing guessers make one and only one guess after receiving all question-answer pairs in a dialogue with the predefined number of rounds. This paper proposes a guessing state for the Guesser, and regards guess as a process with change of guessing state through a dialogue. A guessing state tracking based guess model is therefore proposed. The guessing state is define…
MM-Snowball: Evaluating and Mitigating Hallucination Snowballing in Multimodal Multi-Turn Dialogue
College of Intelligent Robotics and Advanced Manufacturing, Fudan University（复旦大学智能机器人与先进制造学院）；Southern University of Science and Technology（南方科技大学）；TMLR Group, Hong Kong Baptist University（香港 Baptist 大学 TMLR 团体）；MM Lab, CUHK（CUHK 多模态实验室）；RAMS Lab, Huawei Technologies Co., Ltd.（华为技术有限公司 RAMS 实验室）
Grounding natural language instructions on the web to perform previously unseen tasks enables accessibility and automation. We introduce a task and dataset to train AI agents from open-domain, step-by-step instructions originally written for people. We build RUSS (Rapid Universal Support Service) to tackle this problem. RUSS consists of two models: First, a BERT-LSTM with pointers parses instructions to ThingTalk, a domain-specific language we design for grounding natural language on the web. Then, a grounding model retrieves the unique IDs of any webpage elements requested in ThingTalk. RUSS …
Stanford University（斯坦福大学）；Massachusetts Institute of Technology（麻省理工学院）
Grounding object properties and relations in 3D scenes is a prerequisite for a wide range of artificial intelligence tasks, such as visually grounded dialogues and embodied manipulation. However, the variability of the 3D domain induces two fundamental challenges: 1) the expense of labeling and 2) the complexity of 3D grounded language. Hence, essential desiderata for models are to be data-efficient, generalize to different data distributions and tasks with unseen semantic forms, as well as ground complex language semantics (e.g., view-point anchoring and multi-object reference). To address th…
User Satisfaction Estimation (USE) is an important yet challenging task in goal-oriented conversational systems. Whether the user is satisfied with the system largely depends on the fulfillment of the user's needs, which can be implicitly reflected by users' dialogue acts. However, existing studies often neglect the sequential transitions of dialogue act or rely heavily on annotated dialogue act labels when utilizing dialogue acts to facilitate USE. In this paper, we propose a novel framework, namely USDA, to incorporate the sequential dynamics of dialogue acts for predicting user satisfaction…
Beijing University of Posts and Telecommunications（北京邮电大学）；Meituan Group（美团集团）
We propose a novel task, Multi-Document Driven Dialogue (MD3), in which an agent can guess the target document that the user is interested in by leading a dialogue. To benchmark progress, we introduce a new dataset of GuessMovie, which contains 16,881 documents, each describing a movie, and associated 13,434 dialogues. Further, we propose the MD3 model. Keeping guessing the target document in mind, it converses with the user conditioned on both document engagement and user feedback. In order to incorporate large-scale external documents into the dialogue, it pretrains a document representation…
We introduce doc2dial, a new dataset of goal-oriented dialogues that are grounded in the associated documents. Inspired by how the authors compose documents for guiding end users, we first construct dialogue flows based on the content elements that corresponds to higher-level relations across text sections as well as lower-level relations between discourse units within a section. Then we present these dialogue flows to crowd contributors to create conversational utterances. The dataset includes about 4800 annotated conversations with an average of 14 turns that are grounded in over 480 documen…
ChatVTG: Video Temporal Grounding via Chat with Video Dialogue Large Language Models
Institute of Information Science, Beijing Jiaotong University（北京交通大学信息科学研究所）；JD Explore Academy（京东探索研究院）；University of Science and Technology of China（中国科学技术大学）；Horace Mann School（霍勒斯·曼学校）
University of California, Los Angeles（加州大学洛杉矶分校）；Columbia University（哥伦比亚大学）
Building a socially intelligent agent involves many challenges. One of which is to track the agent's mental state transition and teach the agent to make decisions guided by its value like a human. Towards this end, we propose to incorporate mental state simulation and value modeling into dialogue agents. First, we build a hybrid mental state parser that extracts information from both the dialogue and event observations and maintains a graphical representation of the agent's mind; Meanwhile, the transformer-based value model learns human preferences from the human value dataset, ValueNet. Empir…
We consider grounding open domain dialogues with images. Existing work assumes that both an image and a textual context are available, but image-grounded dialogues by nature are more difficult to obtain than textual dialogues. Thus, we propose learning a response generation model with both image-grounded dialogues and textual dialogues by assuming that the visual scene information at the time of a conversation can be represented by an image, and trying to recover the latent images of the textual dialogues through text-to-image generation techniques. The likelihood of the two types of dialogues…
University of Montreal（蒙特利尔大学）；Univ. Lille（里尔大学）；CNRS（法国国家科学研究中心）；Centrale Lille（里尔中央理工学院）；Inria（法国国家信息与自动化研究所）；DeepMind；Twitter
We introduce GuessWhat?!, a two-player guessing game as a testbed for research on the interplay of computer vision and dialogue systems. The goal of the game is to locate an unknown object in a rich image scene by asking a sequence of questions. Higher-level image understanding, like spatial reasoning and language grounding, is required to solve the proposed task. Our key contribution is the collection of a large-scale dataset consisting of 150K human-played games with a total of 800K visual question-answer pairs on 66K images. We explain our design decisions in collecting the dataset and intr…
University of Freiburg（弗赖堡大学）；Toyota Research Institute（丰田研究院）
Controlling robots to perform tasks via natural language is one of the most challenging topics in human-robot interaction. In this work, we present a robot system that follows unconstrained language instructions to pick and place arbitrary objects and effectively resolves ambiguities through dialogues. Our approach infers objects and their relationships from input images and language expressions and can place objects in accordance with the spatial relations expressed by the user. Unlike previous approaches, we consider grounding not only for the picking but also for the placement of everyday o…
Number it: Temporal Grounding Videos like Flipping Manga
Southeast University（东南大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；WeChat Vision, Tencent Inc.（腾讯公司微信视觉部）；University of California, Berkeley（加州大学伯克利分校）
DOGR: Towards Versatile Visual Document Grounding and Referring
Xi’an Jiaotong University（西安交通大学）；ARC Lab, Tencent PCG（腾讯PCG ARC实验室）；City University of Hongkong（香港城市大学）；Institute of Automation, CAS（中国科学院自动化研究所）；Harvard University（哈佛大学）；vivo Mobile Communication Co.（vivo移动通信公司）
GeoPixel: Pixel Grounding Large Multimodal Model in Remote Sensing
Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Australian National University（澳大利亚国立大学）；The University of Western Australia（西澳大利亚大学）
