HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent Enchancement

Hugging Face Daily Papers Papers
video-personalization subject-driven-generation multimodal mllm human-object-interaction self-attention video-generation

Summary

HOMIE is a framework for human-object centric video personalization that integrates MLLM features to improve subject fidelity and interaction patterns, achieving state-of-the-art performance.

Human-object centric video personalization (HOCVP) is a core task within subject-driven video generation. However, existing methods suffer from two key limitations. First, most approaches focusing on inter-subject personalization still struggle to strike a balance between high subject fidelity and accurate interaction patterns between humans and diverse objects, especially when objects represent abstract concepts such as logos. Second, while intra-subject references (e.g., OCR maps, multi-view inputs) are expected to enhance subject fidelity, most existing works lack mechanisms to understand such latent correspondence. To address both challenges, we propose HOMIE, an HOCVP framework that tackles both inter- and intra-subject input settings in a unified manner. Compared to previous approaches, HOMIE proposes a better MLLM integration strategy to extract knowledge of reference-level relationships without compromising the controllability of text encoders or incurring costly re-alignment. Specifically, we introduce global multimodal guidance within self-attention to better align MLLM-derived semantic features with VAE tokens. Furthermore, we propose modality-reference embedding to differentiate tokens from MLLM features and VAE tokens and associate intra-subject reference image tokens. Extensive experiments validate that our method achieves state-of-the-art performance across various HOCVP tasks. Project Page: https://yiyangcai.github.io/homie-page.github.io/
Original Article
View Cached Full Text

Cached at: 07/21/26, 06:35 AM

Paper page - HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent Enchancement

Source: https://huggingface.co/papers/2607.18217

Abstract

Human-objectcentricvideopersonalization(HOCVP)isacoretaskwithinsubject-drivenvideogeneration.However,existingmethodssufferfromtwokeylimitations.First,mostapproachesfocusingoninter-subjectpersonalizationstillstruggletostrikeabalancebetweenhighsubjectfidelityandaccurateinteractionpatternsbetweenhumansanddiverseobjects,especiallywhenobjectsrepresentabstractconceptssuchaslogos.Second,whileintra-subjectreferences(e.g.,OCRmaps,multi-viewinputs)areexpectedtoenhancesubjectfidelity,mostexistingworkslackmechanismstounderstandsuchlatentcorrespondence.Toaddressbothchallenges,weproposeHOMIE,anHOCVPframeworkthattacklesbothinter-andintra-subjectinputsettingsinaunifiedmanner.Comparedtopreviousapproaches,HOMIEproposesabetterMLLMintegrationstrategytoextractknowledgeofreference-levelrelationshipswithoutcompromisingthecontrollabilityoftextencodersorincurringcostlyre-alignment.Specifically,weintroduceglobalmultimodalguidancewithinself-attentiontobetteralignMLLM-derivedsemanticfeatureswithVAEtokens.Furthermore,weproposemodality-referenceembeddingtodifferentiatetokensfromMLLMfeaturesandVAEtokensandassociateintra-subjectreferenceimagetokens.Extensiveexperimentsvalidatethatourmethodachievesstate-of-the-artperformanceacrossvariousHOCVPtasks.ProjectPage:https://yiyangcai.github.io/homie-page.github.io/

View arXiv pageView PDFProject pageGitHub11Add to collection

Get this paper in your agent:

hf papers read 2607\.18217

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2607.18217 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.18217 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.18217 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

PersonaVLM: Long-Term Personalized Multimodal LLMs

Hugging Face Daily Papers

PersonaVLM introduces a personalized multimodal LLM framework that enables long-term user adaptation through memory retention, multi-turn reasoning, and response alignment, outperforming GPT-4o by 5.2% on the new Persona-MME benchmark.

MemLife: Curating and Reasoning over Long-Term Egocentric Video Memories

Hugging Face Daily Papers

MemLife introduces a multimodal memory system for long-term egocentric videos that builds entity-grounded text episodes and retrieves them with a time-indexed agentic reader, improving over training-free baselines by 4.6-12.0% on long-horizon benchmarks. A reinforcement learning framework called MemOpt further optimizes the memory writer for faithfulness and retrievability, yielding consistent 2.7-5.0% gains.