Cover Image

Detached Skip-Links and $R$-Probe: Decoupling Feature Aggregation from Gradient Propagation for MLLM OCR

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yuan, Ziye, Yao, Ruchang, Zheng, Chengxin, Zhao, Yusheng, Dong, Daxiang, Zhang, Ming
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

GT-PCQA: Geometry-Texture Decoupled Point Cloud Quality Assessment with MLLM
by: Zhang, Guohua, et al.
Published: (2026)

Hierarchical Visual Feature Aggregation for OCR-Free Document Understanding
by: Park, Jaeyoo, et al.
Published: (2024)

Predict to Skip: Linear Multistep Feature Forecasting for Efficient Diffusion Transformers
by: Cui, Hanshuai, et al.
Published: (2026)

Qianfan-OCR: A Unified End-to-End Model for Document Intelligence
by: Dong, Daxiang, et al.
Published: (2026)

Reading or Reasoning? Format Decoupled Reinforcement Learning for Document OCR
by: Zhong, Yufeng, et al.
Published: (2025)

UNICBench: UNIfied Counting Benchmark for MLLM
by: Rong, Chenggang, et al.
Published: (2026)

Improving MLLM's Document Image Machine Translation via Synchronously Self-reviewing Its OCR Proficiency
by: Liang, Yupu, et al.
Published: (2025)

Skip and Skip: Segmenting Medical Images with Prompts
by: Chen, Jiawei, et al.
Published: (2024)

Reading Between the Lines: Abstaining from VLM-Generated OCR Errors via Latent Representation Probes
by: Yao, Jihan, et al.
Published: (2025)

Exploring Modality-Aware Fusion and Decoupled Temporal Propagation for Multi-Modal Object Tracking
by: Wang, Shilei, et al.
Published: (2026)

HumanPCR: Probing MLLM Capabilities in Diverse Human-Centric Scenes
by: Li, Keliang, et al.
Published: (2025)

CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM
by: Xu, Jingwei, et al.
Published: (2024)

Temporal Propagation of Asymmetric Feature Pyramid for Surgical Scene Segmentation
by: Yuan, Cheng, et al.
Published: (2025)

Enhancing Feature Fusion of U-like Networks with Dynamic Skip Connections
by: Cao, Yue, et al.
Published: (2025)

Qianfan-VL: Domain-Enhanced Universal Vision-Language Models
by: Dong, Daxiang, et al.
Published: (2025)

ESearch-R1: Learning Cost-Aware MLLM Agents for Interactive Embodied Search via Reinforcement Learning
by: Zhou, Weijie, et al.
Published: (2025)

ProSMA-UNet: Decoder Conditioning for Proximal-Sparse Skip Feature Selection
by: Cheng, Chun-Wun, et al.
Published: (2026)

VRAG-DFD: Verifiable Retrieval-Augmentation for MLLM-based Deepfake Detection
by: Han, Hui, et al.
Published: (2026)

Template-Based Feature Aggregation Network for Industrial Anomaly Detection
by: Luo, Wei, et al.
Published: (2026)

SSI-DM: Singularity Skipping Inversion of Diffusion Models
by: Min, Chen, et al.
Published: (2026)

General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
by: Wei, Haoran, et al.
Published: (2024)

Decouple to Reconstruct: High Quality UHD Restoration via Active Feature Disentanglement and Reversible Fusion
by: Liu, Yidi, et al.
Published: (2025)

SkipSR: Faster Super Resolution with Token Skipping
by: Choudhury, Rohan, et al.
Published: (2025)

Ocean-OCR: Towards General OCR Application via a Vision-Language Model
by: Chen, Song, et al.
Published: (2025)

SkipGS: Post-Densification Backward Skipping for Efficient 3DGS Training
by: Li, Jingxing, et al.
Published: (2026)

VersaViT: Enhancing MLLM Vision Backbones via Task-Guided Optimization
by: Liu, Yikun, et al.
Published: (2026)

DianJin-OCR-R1: Enhancing OCR Capabilities via a Reasoning-and-Tool Interleaved Vision-Language Model
by: Chen, Qian, et al.
Published: (2025)

Enhancing Human Motion Prediction via Multi-range Decoupling Decoding with Gating-adjusting Aggregation
by: Wang, Jiexin, et al.
Published: (2025)

Holistic Reliability Propagation: Decoupling Annotation and Prediction for Robust Noisy-Label
by: Mao, Jingyang, et al.
Published: (2026)

Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent
by: Wu, Junda, et al.
Published: (2025)

OCR-Agent: Agentic OCR with Capability and Memory Reflection
by: Wen, Shimin, et al.
Published: (2026)

OmniOCR: Generalist OCR for Ethnic Minority Languages
by: Liu, Bonan, et al.
Published: (2026)

SkipVAR: Accelerating Visual Autoregressive Modeling via Adaptive Frequency-Aware Skipping
by: Li, Jiajun, et al.
Published: (2025)

GM-Skip: Metric-Guided Transformer Block Skipping for Efficient Vision-Language Models
by: Huang, Lianming, et al.
Published: (2025)

MEJO: MLLM-Engaged Surgical Triplet Recognition via Inter- and Intra-Task Joint Optimization
by: Zhang, Yiyi, et al.
Published: (2025)

Detached and Interactive Multimodal Learning
by: Fan, Yunfeng, et al.
Published: (2024)

Fundus-R1: Training a Fundus-Reading MLLM with Knowledge-Aware Reasoning on Public Data
by: Deng, Yuchuan, et al.
Published: (2026)

GeoAlign: Geometric Feature Realignment for MLLM Spatial Reasoning
by: Liu, Zhaochen, et al.
Published: (2026)

Sce2DriveX: A Generalized MLLM Framework for Scene-to-Drive Learning
by: Zhao, Rui, et al.
Published: (2025)

Diverse Semantics-Guided Feature Alignment and Decoupling for Visible-Infrared Person Re-Identification
by: Dong, Neng, et al.
Published: (2025)