arXiv AI
Jun 30
Multimodal Representation Alignment for Cross-modal Information Retrieval
arXiv:2506. 08774v2 Announce Type: replace-cross Abstract: Different machine learning models can represent the same underlying concept in different ways.
Direct Image-to-Modern Vietnamese Translation of Han-Nom Manuscripts via Multimodal RLHF Preference Alignment
Translating Han-Nom manuscripts into modern Vietnamese is challenging because historical pages are often degraded, the script contains rare logographic characters, and parallel supervision is limited. We propose a multimodal RLHF preference-alignment framework that conditions Vietnamese generation on manuscript images and aligned Han-Nom source text.
Related stories
arXiv AI
Jun 17
Plug-and-Adapt: Multimodal Coreference Resolution at First Sight with a Pretrained Alignment Model
arXiv:2606. 17950v1 Announce Type: cross Abstract: Visual information helps resolve ambiguity in coreference resolution, leading to notable performance gains.
arXiv AI
Jul 3
SEPS: Semantic-enhanced Patch Slimming Framework for fine-grained cross-modal alignment
arXiv:2511. 01390v2 Announce Type: replace-cross Abstract: Fine-grained cross-modal alignment aims to establish precise local correspondences between vision and language, forming a cornerstone for visual question answering and related multimodal applications.
arXiv AI
Jul 16
Inverse-LLaVA: Rethinking Multimodal Alignment via Text-to-Vision Mapping
arXiv:2508. 12466v2 Announce Type: replace-cross Abstract: Traditional multimodal learning approaches rely on alignment pre-training to bridge vision and language modalities, typically by projecting visual features into discrete text token spaces using large-scale image--text data.
arXiv Machine Learning
5d ago
FuseLIP: Multimodal Embeddings via Early Fusion of Discrete Tokens
arXiv:2506. 03096v2 Announce Type: replace-cross Abstract: Contrastive language-image pre-training aligns features of text-image pairs in a common latent space via distinct encoders for each modality.
arXiv AI
Aug 11
TongGuOCR: A Layout-Aware and Token-Augmented OCR Framework for Chinese Historical Documents
arXiv:2608. 07917v1 Announce Type: new Abstract: Chinese historical documents preserve valuable cultural heritage, but many collections remain accessible only as scanned page images, preventing full-text retrieval, collation, and computational analysis.
arXiv AI
Aug 14
Generative Universal Multimodal Retrieval with Dual-role Identifiers
arXiv:2608. 12987v1 Announce Type: cross Abstract: Generative information retrieval (GIR) has emerged as a compelling alternative to the conventional index-retrieve-then-rank retrieval pipeline by training a generator to produce the identifiers of relevant items directly.
arXiv AI
Jul 20
Debiasing Text-to-Image Evaluation via Implicit Cultural Alignment Reward Modeling
arXiv:2607. 15740v1 Announce Type: cross Abstract: As Text-to-Image (T2I) systems rapidly advance, evaluating the cultural authenticity of synthesized content has become increasingly important for fair and trustworthy generative AI.
arXiv AI
Jun 26
Reconstruction Alignment Improves Unified Multimodal Models
arXiv:2509. 07295v4 Announce Type: replace-cross Abstract: Unified multimodal models (UMMs) unify visual understanding and generation within a single architecture.
arXiv AI
Jun 8
Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models
arXiv:2602. 07026v3 Announce Type: replace-cross Abstract: Despite the success of multimodal contrastive learning in aligning visual and linguistic representations, a persistent geometric anomaly, the Modality Gap, remains: embeddings of distinct modalities expressing identical semantics occupy systematically offset regions.
arXiv AI
Aug 12
TongGuOCR: A Layout-Aware and Token-Augmented OCR MLLM for Chinese Historical Documents
arXiv:2608. 07917v2 Announce Type: replace Abstract: Chinese historical documents preserve valuable cultural heritage, but many collections remain accessible only as scanned page images, preventing full-text retrieval, collation, and computational analysis.
arXiv AI
Jul 14
PivotMerge: Bridging Heterogeneous Multimodal Pre-training via Post-Alignment Model Merging
arXiv:2604. 22823v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) rely on multimodal pre-training over diverse data sources, where different datasets often induce complementary cross-modal alignment capabilities.