{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/multimodal-large-language-model/papers/4","list_of":"/task/multimodal-large-language-model","task":"Multimodal Large Language Model","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":4,"pages_in_order":4,"rows_per_page":100,"rows":[301,347],"of":347,"counts":{"archive_papers_tagged":347,"with_a_code_link":160,"where_syntology_ran_a_sample":59,"not_listed_spam_title":0,"listed":347,"listed_where_code_ran":59,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":51,"every_run_a_failure_of_syntologys_instrument":8,"listed_with_a_run_with_no_instrument_failure":51,"listed_every_run_a_failure_of_syntologys_instrument":8,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/multimodal-large-language-model","prev":"/task/multimodal-large-language-model/papers/3","next":null,"papers":[{"url":null,"slug":"voldoger-llm-assisted-datasets-for-domain","title":"VolDoGer: LLM-assisted Datasets for Domain Generalization in Vision-Language Tasks","date":"2024-07-29","arxiv_id":"2407.19795","repositories_listed":0,"syntology":null},{"url":null,"slug":"llava-read-enhancing-reading-ability-of","title":"LLaVA-Read: Enhancing Reading Ability of Multimodal Language Models","date":"2024-07-27","arxiv_id":"2407.19185","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-based-unsupervised-disentangled","title":"Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models","date":"2024-07-26","arxiv_id":"2407.18999","repositories_listed":0,"syntology":null},{"url":null,"slug":"dallah-a-dialect-aware-multimodal-large","title":"Dallah: A Dialect-Aware Multimodal Large Language Model for Arabic","date":"2024-07-25","arxiv_id":"2407.18129","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-neural-matrix-decomposition-recommender","title":"A Neural Matrix Decomposition Recommender System Model based on the Multimodal Large Language Model","date":"2024-07-12","arxiv_id":"2407.08942","repositories_listed":0,"syntology":null},{"url":null,"slug":"genartist-multimodal-llm-as-an-agent-for","title":"GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing","date":"2024-07-08","arxiv_id":"2407.05600","repositories_listed":0,"syntology":null},{"url":null,"slug":"mobileflow-a-multimodal-llm-for-mobile-gui","title":"MobileFlow: A Multimodal LLM For Mobile GUI Agent","date":"2024-07-05","arxiv_id":"2407.04346","repositories_listed":0,"syntology":null},{"url":null,"slug":"mrir-integrating-multimodal-insights-for","title":"MRIR: Integrating Multimodal Insights for Diffusion-based Realistic Image Restoration","date":"2024-07-04","arxiv_id":"2407.03635","repositories_listed":0,"syntology":null},{"url":null,"slug":"guardrails-for-avoiding-harmful-medical","title":"Guardrails for avoiding harmful medical product recommendations and off-label promotion in generative AI models","date":"2024-06-24","arxiv_id":"2406.16455","repositories_listed":0,"syntology":null},{"url":null,"slug":"mr-mllm-mutual-reinforcement-of-multimodal","title":"MR-MLLM: Mutual Reinforcement of Multimodal Comprehension and Vision Perception","date":"2024-06-22","arxiv_id":"2406.15768","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-radiotherapy-treatment-planning","title":"Automated radiotherapy treatment planning guided by GPT-4Vision","date":"2024-06-21","arxiv_id":"2406.15609","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-solution-for-cvpr2024-foundational-few","title":"The Solution for CVPR2024 Foundational Few-Shot Object Detection Challenge","date":"2024-06-18","arxiv_id":"2406.12225","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-llm-jailbreaking-by-introducing","title":"Efficient Indirect LLM Jailbreak via Multimodal-LLM Jailbreak","date":"2024-05-30","arxiv_id":"2405.20015","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-corrected-multimodal-large-language","title":"Self-Corrected Multimodal Large Language Model for End-to-End Robot Manipulation","date":"2024-05-27","arxiv_id":"2405.17418","repositories_listed":0,"syntology":null},{"url":"/paper/aligngpt-multi-modal-large-language-models","slug":"aligngpt-multi-modal-large-language-models","title":"AlignGPT: Multi-modal Large Language Models with Adaptive Alignment Capability","date":"2024-05-23","arxiv_id":"2405.14129","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-of-thought-step-by-step-video-reasoning","title":"Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition","date":"2024-05-07","arxiv_id":"2501.03230","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-large-language-model-is-a-human","title":"Multimodal Large Language Model is a Human-Aligned Annotator for Text-to-Image Generation","date":"2024-04-23","arxiv_id":"2404.15100","repositories_listed":0,"syntology":null},{"url":null,"slug":"ragar-your-falsehood-radar-rag-augmented","title":"RAGAR, Your Falsehood Radar: RAG-Augmented Reasoning for Political Fact-Checking using Multimodal Large Language Models","date":"2024-04-18","arxiv_id":"2404.12065","repositories_listed":0,"syntology":null},{"url":null,"slug":"guide-graphical-user-interface-data-for","title":"GUIDE: Graphical User Interface Data for Execution","date":"2024-04-09","arxiv_id":"2404.16048","repositories_listed":0,"syntology":null},{"url":null,"slug":"unbridled-icarus-a-survey-of-the-potential","title":"Unbridled Icarus: A Survey of the Potential Perils of Image Inputs in Multimodal Large Language Model Security","date":"2024-04-08","arxiv_id":"2404.05264","repositories_listed":0,"syntology":null},{"url":null,"slug":"semgrasp-semantic-grasp-generation-via","title":"SemGrasp: Semantic Grasp Generation via Language Aligned Discretization","date":"2024-04-04","arxiv_id":"2404.03590","repositories_listed":0,"syntology":null},{"url":null,"slug":"hear-me-see-me-understand-me-audio-visual","title":"Hear Me, See Me, Understand Me: Audio-Visual Autism Behavior Recognition","date":"2024-03-22","arxiv_id":"2406.02554","repositories_listed":0,"syntology":null},{"url":"/paper/vl-mamba-exploring-state-space-models-for","slug":"vl-mamba-exploring-state-space-models-for","title":"VL-Mamba: Exploring State Space Models for Multimodal Learning","date":"2024-03-20","arxiv_id":"2403.13600","repositories_listed":0,"syntology":null},{"url":"/paper/strengthening-multimodal-large-language-model","slug":"strengthening-multimodal-large-language-model","title":"Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization","date":"2024-03-13","arxiv_id":"2403.08730","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-transformer-for-comics-text-cloze","title":"Multimodal Transformer for Comics Text-Cloze","date":"2024-03-06","arxiv_id":"2403.03719","repositories_listed":0,"syntology":null},{"url":null,"slug":"sniffer-multimodal-large-language-model-for","title":"SNIFFER: Multimodal Large Language Model for Explainable Out-of-Context Misinformation Detection","date":"2024-03-05","arxiv_id":"2403.03170","repositories_listed":0,"syntology":null},{"url":null,"slug":"miko-multimodal-intention-knowledge","title":"MIKO: Multimodal Intention Knowledge Distillation from Large Language Models for Social-Media Commonsense Discovery","date":"2024-02-28","arxiv_id":"2402.18169","repositories_listed":0,"syntology":null},{"url":null,"slug":"mmmmodal-multi-images-multi-audio-multi-turn","title":"MMMModal -- Multi-Images Multi-Audio Multi-turn Multi-Modal","date":"2024-02-17","arxiv_id":"2402.11297","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-question-answering-instruction","title":"Visual Question Answering Instruction: Unlocking Multimodal Large Language Model To Domain-Specific Visual Multitasks","date":"2024-02-13","arxiv_id":"2402.08360","repositories_listed":0,"syntology":null},{"url":null,"slug":"lumos-empowering-multimodal-llms-with-scene","title":"Lumos : Empowering Multimodal LLMs with Scene Text Recognition","date":"2024-02-12","arxiv_id":"2402.08017","repositories_listed":0,"syntology":null},{"url":null,"slug":"llava-docent-instruction-tuning-with","title":"LLaVA-Docent: Instruction Tuning with Multimodal Large Language Model to Support Art Appreciation Education","date":"2024-02-09","arxiv_id":"2402.06264","repositories_listed":0,"syntology":null},{"url":null,"slug":"llava-mole-sparse-mixture-of-lora-experts-for","title":"LLaVA-MoLE: Sparse Mixture of LoRA Experts for Mitigating Data Conflicts in Instruction Finetuning MLLMs","date":"2024-01-29","arxiv_id":"2401.16160","repositories_listed":0,"syntology":null},{"url":null,"slug":"mllmreid-multimodal-large-language-model","title":"MLLMReID: Multimodal Large Language Model-based Person Re-identification","date":"2024-01-24","arxiv_id":"2401.13201","repositories_listed":0,"syntology":null},{"url":null,"slug":"unimo-g-unified-image-generation-through","title":"UNIMO-G: Unified Image Generation through Multimodal Conditional Diffusion","date":"2024-01-24","arxiv_id":"2401.13388","repositories_listed":0,"syntology":null},{"url":null,"slug":"codi-2-in-context-interleaved-and-interactive-1","title":"CoDi-2: In-Context Interleaved and Interactive Any-to-Any Generation","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"manipllm-embodied-multimodal-large-language","title":"ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation","date":"2023-12-24","arxiv_id":"2312.16217","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-visual-llm-for-video-understanding","title":"Audio-Visual LLM for Video Understanding","date":"2023-12-11","arxiv_id":"2312.06720","repositories_listed":0,"syntology":null},{"url":null,"slug":"etc-temporal-boundary-expand-then-clarify-for","title":"EtC: Temporal Boundary Expand then Clarify for Weakly Supervised Video Grounding with Multimodal Large Language Model","date":"2023-12-05","arxiv_id":"2312.02483","repositories_listed":0,"syntology":null},{"url":null,"slug":"medxchat-bridging-cxr-modalities-with-a","title":"MedXChat: A Unified Multimodal Large Language Model Framework towards CXRs Understanding and Generation","date":"2023-12-04","arxiv_id":"2312.02233","repositories_listed":0,"syntology":null},{"url":null,"slug":"codi-2-in-context-interleaved-and-interactive","title":"CoDi-2: In-Context, Interleaved, and Interactive Any-to-Any Generation","date":"2023-11-30","arxiv_id":"2311.18775","repositories_listed":0,"syntology":null},{"url":null,"slug":"gpt4video-a-unified-multimodal-large-language","title":"GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware Generation","date":"2023-11-25","arxiv_id":"2311.16511","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-to-bridge-the-gap-between-modalities-a","title":"How to Bridge the Gap between Modalities: Survey on Multimodal Large Language Model","date":"2023-11-10","arxiv_id":"2311.07594","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-large-language-model-for-visual","title":"Multimodal Large Language Model for Visual Navigation","date":"2023-10-12","arxiv_id":"2310.08669","repositories_listed":0,"syntology":null},{"url":null,"slug":"comics-for-everyone-generating-accessible","title":"Comics for Everyone: Generating Accessible Text Descriptions for Comic Strips","date":"2023-10-01","arxiv_id":"2310.00698","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-the-catastrophic-forgetting-in","title":"Investigating the Catastrophic Forgetting in Multimodal Large Language Models","date":"2023-09-19","arxiv_id":"2309.10313","repositories_listed":0,"syntology":null},{"url":null,"slug":"imaginations-of-wall-e-reconstructing","title":"Imaginations of WALL-E : Reconstructing Experiences with an Imagination-Inspired Module for Advanced AI Systems","date":"2023-08-20","arxiv_id":"2308.10354","repositories_listed":0,"syntology":null},{"url":null,"slug":"chatspot-bootstrapping-multimodal-llms-via","title":"ChatSpot: Bootstrapping Multimodal LLMs via Precise Referring Instruction Tuning","date":"2023-07-18","arxiv_id":"2307.09474","repositories_listed":0,"syntology":null}],"record_sha256":"94805553cdac030067b6cde431db6a23733525d6bbd1a296a9a80d8b75490d9d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}