{"total":51,"rows":[{"id":"2110.08118","title":"Few-Shot Bot: Prompt-Based Learning for Dialogue Systems","created":"2021-10-15","cited_by_count":64,"area":null},{"id":"2106.02787","title":"BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modeling","created":"2021-06-05","cited_by_count":56,"area":null},{"id":"2209.06664","title":"SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation","created":"2022-09-14","cited_by_count":34,"area":null},{"id":"2209.06638","title":"SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding","created":"2022-09-14","cited_by_count":28,"area":null},{"id":"2506.05904","title":"Proactive Assistant Dialogue Generation from Streaming Egocentric Videos","created":"2025-06-06","cited_by_count":28,"area":null},{"id":"2403.10943","title":"MIntRec2.0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in Conversations","created":"2024-03-16","cited_by_count":26,"area":null},{"id":"2207.14627","title":"\"Do you follow me?\": A Survey of Recent Approaches in Dialogue State Tracking","created":"2022-07-29","cited_by_count":22,"area":null},{"id":"2305.14839","title":"PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts","created":"2023-05-24","cited_by_count":19,"area":null},{"id":"2311.09008","title":"End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions","created":"2023-11-15","cited_by_count":17,"area":null},{"id":"2205.06907","title":"Multimodal Conversational AI: A Survey of Datasets and Approaches","created":"2022-05-13","cited_by_count":16,"area":null},{"id":"2209.12953","title":"Dialog Acts for Task-Driven Embodied Agents","created":"2022-09-26","cited_by_count":13,"area":null},{"id":"2112.08351","title":"Database Search Results Disambiguation for Task-Oriented Dialog Systems","created":"2021-12-15","cited_by_count":10,"area":null},{"id":"2211.11617","title":"CGoDial: A Large-Scale Benchmark for Chinese Goal-oriented Dialog Evaluation","created":"2022-11-21","cited_by_count":9,"area":null},{"id":"2506.04089","title":"AmbiK: Dataset of Ambiguous Tasks in Kitchen Environment","created":"2025-06-04","cited_by_count":9,"area":null},{"id":"2403.19259","title":"J-CRe3: A Japanese Conversation Dataset for Real-world Reference Resolution","created":"2024-03-28","cited_by_count":7,"area":null},{"id":"2206.07898","title":"Multimodal Dialogue State Tracking","created":"2022-06-16","cited_by_count":6,"area":null},{"id":"2301.01949","title":"SPRING: Situated Conversation Agent Pretrained with Multimodal Questions from Incremental Layout Graph","created":"2023-01-05","cited_by_count":6,"area":null},{"id":"2109.12913","title":"The JDDC 2.0 Corpus: A Large-Scale Multimodal Multi-Turn Chinese Dialogue Dataset for E-commerce Customer Service","created":"2021-09-27","cited_by_count":5,"area":null},{"id":"2604.09698","title":"Evaluating Scene-based In-Situ Item Labeling for Immersive Conversational Recommendation","created":"2026-04-06","cited_by_count":5,"area":null},{"id":"2401.17039","title":"Taking Action Towards Graceful Interaction: The Effects of Performing Actions on Modelling Policies for Instruction Clarification Requests","created":"2024-01-30","cited_by_count":4,"area":null},{"id":"2402.10137","title":"TOAD: Task-Oriented Automatic Dialogs with Diverse Response Styles","created":"2024-02-15","cited_by_count":4,"area":null},{"id":"2307.15554","title":"'What are you referring to?' Evaluating the Ability of Multi-Modal Dialogue Models to Process Clarificational Exchanges","created":"2023-07-28","cited_by_count":3,"area":null},{"id":"2309.11065","title":"UniPCM: Universal Pre-trained Conversation Model with Task-aware Automatic Prompt","created":"2023-09-20","cited_by_count":3,"area":null},{"id":"2402.13146","title":"OLViT: Multi-Modal State Tracking via Attention-Based Embeddings for Video-Grounded Dialog","created":"2024-02-20","cited_by_count":3,"area":null},{"id":"2407.02218","title":"Multi-Modal Video Dialog State Tracking in the Wild","created":"2024-07-02","cited_by_count":3,"area":null},{"id":"2506.00421","title":"Enabling Chatbots with Eyes and Ears: An Immersive Multimodal Conversation System for Dynamic Interactions","created":"2025-05-31","cited_by_count":3,"area":null},{"id":"2112.03521","title":"UNITER-Based Situated Coreference Resolution with Rich Multimodal Input","created":"2021-12-07","cited_by_count":2,"area":null},{"id":"2202.12645","title":"Exploring Multi-Modal Representations for Ambiguity Detection & Coreference Resolution in the SIMMC 2.0 Challenge","created":"2022-02-25","cited_by_count":2,"area":null},{"id":"2504.17390","title":"PicPersona-TOD : A Dataset for Personalizing Utterance Style in Task-Oriented Dialogue with Image Persona","created":"2025-04-24","cited_by_count":2,"area":null},{"id":"2112.05328","title":"Multimodal Interactions Using Pretrained Unimodal Models for SIMMC 2.0","created":"2021-12-10","cited_by_count":1,"area":null},{"id":"2211.03940","title":"Tell Your Story: Task-Oriented Dialogs for Interactive Content Creation","created":"2022-11-08","cited_by_count":1,"area":null},{"id":"2302.14680","title":"Which One Are You Referring To? Multimodal Object Identification in Situated Dialogue","created":"2023-02-28","cited_by_count":1,"area":null},{"id":"2307.04907","title":"SimpleMTOD: A Simple Language Model for Multimodal Task-Oriented Dialogue with Symbolic Scene Representation","created":"2023-07-10","cited_by_count":1,"area":null},{"id":"2309.05162","title":"Collecting Visually-Grounded Dialogue with A Game Of Sorts","created":"2023-09-10","cited_by_count":1,"area":null},{"id":"2401.02417","title":"Task Oriented Dialogue as a Catalyst for Self-Supervised Automatic Speech Recognition","created":"2024-01-04","cited_by_count":1,"area":null},{"id":"2504.14321","title":"Multimodal Coreference Resolution for Chinese Social Media Dialogues: Dataset and Benchmark Approach","created":"2025-04-19","cited_by_count":1,"area":null},{"id":"2608.06718","title":"Do Audio Language Models Use Paralinguistic Evidence? Counterfactual Audits for Response Evaluation","created":"2026-08-07","cited_by_count":1,"area":null},{"id":"2609.21392","title":"Omni Demand Understanding: A Benchmark for Contextual User-Intent Inference in Multimodal Interaction","created":"2026-09-18","cited_by_count":1,"area":null},{"id":"2111.11576","title":"Building Goal-Oriented Dialogue Systems with Situated Visual Context","created":"2021-11-22","cited_by_count":0,"area":null},{"id":"2203.08362","title":"Spot the Difference: A Cooperative Object-Referring Game in Non-Perfectly Co-Observable Scene","created":"2022-03-16","cited_by_count":0,"area":null},{"id":"2208.14884","title":"GRILLBot: An Assistant for Real-World Tasks with Neural Semantic Parsing and Graph-Based Representations","created":"2022-08-31","cited_by_count":0,"area":null},{"id":"2211.08462","title":"Navigating Connected Memories with a Task-oriented Dialog System","created":"2022-11-15","cited_by_count":0,"area":null},{"id":"2305.18212","title":"Multimodal Recommendation Dialog with Subjective Preference: A New Challenge and Benchmark","created":"2023-05-26","cited_by_count":0,"area":null},{"id":"2309.07387","title":"VDialogUE: A Unified Evaluation Benchmark for Visually-grounded Dialogue","created":"2023-09-14","cited_by_count":0,"area":null},{"id":"2406.06438","title":"Multimodal Contextualized Semantic Parsing from Speech","created":"2024-06-10","cited_by_count":0,"area":null},{"id":"2505.11726","title":"Disambiguating Reference in Visually Grounded Dialogues through Joint Modeling of Textual and Multimodal Semantic Structures","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2510.21761","title":"J-ORA: A Framework and Multimodal Dataset for Japanese Object Identification, Reference, Action Prediction in Robot Perception","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2606.17950","title":"Plug-and-Adapt: Multimodal Coreference Resolution at First Sight with a Pretrained Alignment Model","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2609.18249","title":"Re2A: Situated Conversational Recommendation via Rubric-based Preference Reasoning and Alignment","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2610.05526","title":"Have I Scene This Before? Spatially Grounded Conversational Memory for Complex Queries in Egocentric Assistants","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.19723","title":"Recognizing Dialogue Ambiguity via Candidate Set Visual Grounding","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}