{"url":"/task/multimodal-interaction","name":"multimodal interaction","slug":"multimodal-interaction","description_markdown":null,"categories":[{"name":"Robots","url":"/area/robots"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":106,"papers_with_code":41,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":41,"tagged_in_all":106,"items":[{"url":"/paper/vilt-vision-and-language-transformer-without","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","date":"2021-02-05","arxiv_id":"2102.03334","repositories_listed":6,"syntology":{"n":4,"n_ran":1,"n_unverified":3,"n_pointer_only":1}},{"url":"/paper/stream-omni-simultaneous-multimodal","title":"Stream-Omni: Simultaneous Multimodal Interactions with Large Language-Vision-Speech Model","date":"2025-06-16","arxiv_id":"2506.13642","repositories_listed":2,"syntology":null},{"url":"/paper/mm-bigbench-evaluating-multimodal-models-on","title":"MM-BigBench: Evaluating Multimodal Models on Multimodal Content Comprehension Tasks","date":"2023-10-13","arxiv_id":"2310.09036","repositories_listed":2,"syntology":null},{"url":"/paper/chartsketcher-reasoning-with-multimodal","title":"ChartSketcher: Reasoning with Multimodal Feedback and Reflection for Chart Understanding","date":"2025-05-25","arxiv_id":"2505.19076","repositories_listed":1,"syntology":null},{"url":"/paper/i2moe-interpretable-multimodal-interaction","title":"I2MoE: Interpretable Multimodal Interaction-aware Mixture-of-Experts","date":"2025-05-25","arxiv_id":"2505.19190","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":4}},{"url":"/paper/ming-lite-uni-advancements-in-unified","title":"Ming-Lite-Uni: Advancements in Unified Architecture for Natural Multimodal Interaction","date":"2025-05-05","arxiv_id":"2505.02471","repositories_listed":1,"syntology":null},{"url":"/paper/ovtr-end-to-end-open-vocabulary-multiple","title":"OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer","date":"2025-03-13","arxiv_id":"2503.10616","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/towards-explainable-multimodal-depression","title":"Towards Explainable Multimodal Depression Recognition for Clinical Interviews","date":"2025-01-27","arxiv_id":"2501.16106","repositories_listed":1,"syntology":null},{"url":"/paper/spider-any-to-many-multimodal-llm","title":"Spider: Any-to-Many Multimodal LLM","date":"2024-11-14","arxiv_id":"2411.09439","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-multimodal-query-representation-via","title":"MIRe: Enhancing Multimodal Queries Representation via Fusion-Free Modality Interaction for Multimodal Retrieval","date":"2024-11-13","arxiv_id":"2411.08334","repositories_listed":1,"syntology":null},{"url":"/paper/foundations-and-recent-trends-in-multimodal-1","title":"Foundations and Recent Trends in Multimodal Mobile Agents: A Survey","date":"2024-11-04","arxiv_id":"2411.02006","repositories_listed":1,"syntology":null},{"url":"/paper/llms-can-evolve-continually-on-modality-for-x","title":"LLMs Can Evolve Continually on Modality for X-Modal Reasoning","date":"2024-10-26","arxiv_id":"2410.20178","repositories_listed":1,"syntology":null},{"url":"/paper/spatio-temporal-3d-point-clouds-from-wifi-csi","title":"Spatio-Temporal 3D Point Clouds from WiFi-CSI Data via Transformer Networks","date":"2024-10-07","arxiv_id":"2410.16303","repositories_listed":1,"syntology":null},{"url":"/paper/mamba-enhanced-text-audio-video-alignment","title":"Mamba-Enhanced Text-Audio-Video Alignment Network for Emotion Recognition in Conversations","date":"2024-09-08","arxiv_id":"2409.05243","repositories_listed":1,"syntology":null},{"url":"/paper/dissecting-dissonance-benchmarking-large","title":"Dissecting Dissonance: Benchmarking Large Multimodal Models Against Self-Contradictory Instructions","date":"2024-08-02","arxiv_id":"2408.01091","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/unimel-a-unified-framework-for-multimodal","title":"UniMEL: A Unified Framework for Multimodal Entity Linking with Large Language Models","date":"2024-07-23","arxiv_id":"2407.16160","repositories_listed":1,"syntology":null},{"url":"/paper/tip-tabular-image-pre-training-for-multimodal","title":"TIP: Tabular-Image Pre-training for Multimodal Classification with Incomplete Data","date":"2024-07-10","arxiv_id":"2407.07582","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/empathic-grounding-explorations-using","title":"Empathic Grounding: Explorations using Multimodal Interaction and Large Language Models with Conversational Agents","date":"2024-07-01","arxiv_id":"2407.01824","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-and-mitigating-the-multimodal","title":"Investigating and Mitigating the Multimodal Hallucination Snowballing in Large Vision-Language Models","date":"2024-06-30","arxiv_id":"2407.00569","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":2}},{"url":"/paper/look-m-look-once-optimization-in-kv-cache-for","title":"LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference","date":"2024-06-26","arxiv_id":"2406.18139","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/narrative-action-evaluation-with-prompt","title":"Narrative Action Evaluation with Prompt-Guided Multimodal Interaction","date":"2024-04-22","arxiv_id":"2404.14471","repositories_listed":1,"syntology":null},{"url":"/paper/cooperative-sentiment-agents-for-multimodal","title":"Cooperative Sentiment Agents for Multimodal Sentiment Analysis","date":"2024-04-19","arxiv_id":"2404.12642","repositories_listed":1,"syntology":null},{"url":"/paper/draw-and-understand-leveraging-visual-prompts","title":"Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want","date":"2024-03-29","arxiv_id":"2403.20271","repositories_listed":1,"syntology":null},{"url":"/paper/agent-ai-surveying-the-horizons-of-multimodal","title":"Agent AI: Surveying the Horizons of Multimodal Interaction","date":"2024-01-07","arxiv_id":"2401.03568","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_unverified":3,"n_pointer_only":7}},{"url":"/paper/mmoe-mixture-of-multimodal-interaction","title":"MMoE: Enhancing Multimodal Models with Mixtures of Multimodal Interaction Experts","date":"2023-11-16","arxiv_id":"2311.09580","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":5}},{"url":"/paper/dialogue-based-generation-of-self-driving","title":"Dialogue-based generation of self-driving simulation scenarios using Large Language Models","date":"2023-10-26","arxiv_id":"2310.17372","repositories_listed":1,"syntology":null},{"url":"/paper/cfn-esa-a-cross-modal-fusion-network-with","title":"CFN-ESA: A Cross-Modal Fusion Network with Emotion-Shift Awareness for Dialogue Emotion Recognition","date":"2023-07-28","arxiv_id":"2307.15432","repositories_listed":1,"syntology":null},{"url":"/paper/multi-grained-multimodal-interaction-network","title":"Multi-Grained Multimodal Interaction Network for Entity Linking","date":"2023-07-19","arxiv_id":"2307.09721","repositories_listed":1,"syntology":null},{"url":"/paper/a-facial-expression-aware-multimodal-multi","title":"A Facial Expression-Aware Multimodal Multi-task Learning Framework for Emotion Recognition in Multi-party Conversations","date":"2023-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/generative-multimodal-entity-linking","title":"Generative Multimodal Entity Linking","date":"2023-06-22","arxiv_id":"2306.12725","repositories_listed":1,"syntology":null}],"syntology_records":9,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}