ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:

20 results for “Multimodal alignment”

CS papers only

Hybrid search: Keyword + semantic, ranked by combined score.ⓘ

Want pure semantic search? Try claim verification →

cs.CVcs.CLcs.LGEmpiricalRecentAug 11, 2026

MultiModal Code-Switching: Interleaving Visual Objects into Language for Explicit Object-Level Alignment

Changhao Xiang, Shangyu Xing, Zhen Wu, Jianbing Zhang +1 more

This paper introduces MultiModal Code-Switching (MMCS), a new pretraining paradigm for multimodal large language models that provides explicit object-level supervision and improves visual grounding an…

View →
cs.AIcs.CVcs.LGEmpiricalRecentNov 6, 2026

Flow-Guided Target-Space Alignment via Path Consistency

Ruizhi Yuan, Zeqiu Yu, Wei Gao, Wei Chen +2 more

This paper proposes a flow-guided target-space alignment method called FlowAlign that improves instance-level correspondence while preserving target-space structure in multimodal alignment problems.

View →
cs.LGEmpiricalRecentJun 9, 2026

When to Align, When to Predict: A Phase Diagram for Multimodal Learning

Ilay Kamai, Hugues Van Assel, Aviv Regev, Hagai B. Perets +1 more

This paper develops a unified linear framework to diagnose when cross-modal alignment and prediction succeed or fail in multimodal representation learning.

View →
cs.LGcs.AIEmpiricalRecentJun 10, 2026

Latent World Recovery for Multimodal Learning with Missing Modalities

Hui Wang, Tianyu Ren, Joseph Butler, Christopher Baker +2 more

The paper proposes a framework for multimodal learning under missing modalities, called Latent World Recovery (LWR), which aligns modality-specific embeddings in a shared latent space and fuses availa…

View →
cs.CLRecentJun 1, 2026

When Meaning Travels: A Granular Lens on Hybrid-MoE's Role in Idiomatic Understanding for Language Models

Sarmistha Das, Vaibhav Vishal, Shreyas Guha, Amaan Ali +2 more

This paper introduces a Hybrid Mixture-of-Experts (HybridMoE) framework and a specialized corpus (Varnika) to significantly improve language models' ability to understand and retain figurative, cultur…

View →
cs.CLeess.ASEmpiricalRecentJun 9, 2026

Multilingual Word-Level Forced Alignment with Self-Supervised Representations and Learned Dynamic Programming

Roy Weber, Meidan Zehavi, Rotem Rousso, Joseph Keshet

Multilingual word-level forced alignment

View →
cs.CVEmpiricalRecentJul 2, 2026

Alignment Is All You Need For X-to-4D Generation

Qiaowei Miao, Kehan Li, Yawei Luo, Yi Yang

This paper introduces Align4D, a framework for generating coherent video-3D pairs using any-modal input, achieving state-of-the-art quality and consistency in X-to-4D generation.

View →
cs.LGcs.AIcs.CRMay 11, 2026

Leveraging RAG for Training-Free Alignment of LLMs

John T. Halloran

The paper introduces RAG-Pref, a novel, training-free Retrieval Augmented Generation (RAG) method for preference alignment that significantly improves LLM refusal guardrails against agentic attacks wi…

View →
cs.SDEmpiricalRecentJun 18, 2026

MixProLAP: Mixture-Induced Uncertainty Modeling for Probabilistic Language-Audio Pretraining

Yu Nakagome, Jaesong Lee, Soo-Whan Chung

Proposes a probabilistic audio-language pretraining framework to model many-to-many correspondence ambiguity in audio-text alignment.

View →
eess.AScs.CLcs.SDEmpiricalRecentJun 23, 2026

Progressive Alignment Objectives for Aligner-Encoder based ASR

Jaeyong Lee, Masato Mimura, Takafumi Moriya

One sentence describing what this paper does

View →
cs.CVcs.AIRecentMay 30, 2026

V-LynX: Token Interface Alignment for Video+X LLMs

Jungin Park, Jiyoung Lee, Kwanghoon Sohn

V-LynX is a framework that enhances Video LLMs by integrating new modalities into their existing token interface, achieving state-of-the-art performance across diverse video understanding tasks.

View →
cs.DCcs.AIRecentJun 1, 2026

Boosting Multimodal Federated Learning via Chained Modality Optimization

Zixin Zhang, Fan Qi, Shuai Li, Xiaoshan Yang +1 more

The paper proposes FedMChain, a novel federated learning framework that structures multimodal training into sequential phases to mitigate modality competition and improve model performance while reduc…

View →
eess.AScs.CLcs.SDEmpiricalRecentJun 24, 2026

Fully Differentiable Neural Forced Alignment via Soft Dynamic Programming

Rotem Rousso, Eyal Cohen, Joseph Keshet

The authors propose an end-to-end neural architecture for phoneme alignment that outperforms the current state of the art.

View →
cs.CLcs.AIRecentMay 30, 2026

MLLM-Microscope: Unlocking Hidden Structure Within Multimodal Large Language Models

Ravil Mussabayev, Rustam Mussabayev

The paper introduces MLLM-Microscope, a system that analyzes the internal structure of multimodal large language models (MLLMs), finding that modality fusion significantly impacts the linearity and di…

View →
cs.SDcs.CLeess.ASEmpiricalRecentOct 20, 2026

Uncovering Audio-Text Alignment in Large Audio-Language Models through Cross-Modal Concept Neurons

Tzu-Quan Lin, Chih-Kai Yang, Yi-Cheng Lin, Hao Tang +1 more

This paper investigates how audio and text representations are integrated in large audio-language models.

View →