Cover Image

InfiniteVL: Synergizing Linear and Sparse Attention for Highly-Efficient, Unlimited-Input Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tao, Hongyuan, Liao, Bencheng, Chen, Shaoyu, Yin, Haoran, Zhang, Qian, Liu, Wenyu, Wang, Xinggang
Format:	Preprint
Published:	2025
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

DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models
by: Zeng, Lunbin, et al.
Published: (2025)

Multimodal Mamba: Decoder-only Multimodal State Space Model via Quadratic to Linear Distillation
by: Liao, Bencheng, et al.
Published: (2025)

MaTVLM: Hybrid Mamba-Transformer for Efficient Vision-Language Modeling
by: Li, Yingyue, et al.
Published: (2025)

Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving
by: Jiang, Bo, et al.
Published: (2024)

OmniMamba: Efficient and Unified Multimodal Understanding and Generation via State Space Models
by: Zou, Jialv, et al.
Published: (2025)

ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attention
by: Liao, Bencheng, et al.
Published: (2024)

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
by: Zhu, Lianghui, et al.
Published: (2024)

VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning
by: Jiang, Bo, et al.
Published: (2024)

MIM4D: Masked Modeling with Multi-View Video for Autonomous Driving Representation Learning
by: Zou, Jialv, et al.
Published: (2024)

Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction
by: Liao, Bencheng, et al.
Published: (2023)

MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction
by: Liao, Bencheng, et al.
Published: (2023)

DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention
by: Zhu, Lianghui, et al.
Published: (2024)

DiffusionDriveV2: Reinforcement Learning-Constrained Truncated Diffusion Modeling in End-to-End Autonomous Driving
by: Zou, Jialv, et al.
Published: (2025)

Polar Parametrization for Vision-based Surround-View 3D Detection
by: Chen, Shaoyu, et al.
Published: (2022)

DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving
by: Liao, Bencheng, et al.
Published: (2024)

AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning
by: Jiang, Bo, et al.
Published: (2025)

RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning
by: Gao, Hao, et al.
Published: (2025)

PersonViT: Large-scale Self-supervised Vision Transformer for Person Re-Identification
by: Hu, Bin, et al.
Published: (2024)

RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework
by: Gao, Hao, et al.
Published: (2026)

ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving
by: Zheng, Zhiyu, et al.
Published: (2025)

A-VL: Adaptive Attention for Large Vision-Language Models
by: Zhang, Junyang, et al.
Published: (2024)

Cross-Layer Attentive Feature Upsampling for Low-latency Semantic Segmentation
by: Cheng, Tianheng, et al.
Published: (2026)

SDAR-VL: Stable and Efficient Block-wise Diffusion for Vision-Language Understanding
by: Cheng, Shuang, et al.
Published: (2025)

ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning
by: Hao, Zhiwei, et al.
Published: (2024)

Firebolt-VL: Efficient Vision-Language Understanding with Cross-Modality Modulation
by: Trinh, Quoc-Huy, et al.
Published: (2026)

SAIL-VL2 Technical Report
by: Yin, Weijie, et al.
Published: (2025)

Towards Fast, Memory-based and Data-Efficient Vision-Language Policy
by: Li, Haoxuan, et al.
Published: (2025)

GaraMoSt: Parallel Multi-Granularity Motion and Structural Modeling for Efficient Multi-Frame Interpolation in DSA Images
by: Xu, Ziyang, et al.
Published: (2024)

GenderBias-\emph{VL}: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing
by: Xiao, Yisong, et al.
Published: (2024)

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

FCoT-VL:Advancing Text-oriented Large Vision-Language Models with Efficient Visual Token Compression
by: Li, Jianjian, et al.
Published: (2025)

LEO-VL: Efficient Scene Representation for Scalable 3D Vision-Language Learning
by: Huang, Jiangyong, et al.
Published: (2025)

DeltaMIL: Gated Memory Integration for Efficient and Discriminative Whole Slide Image Analysis
by: Zhu, Yueting, et al.
Published: (2025)

ViTGaze: Gaze Following with Interaction Features in Vision Transformers
by: Song, Yuehao, et al.
Published: (2024)

VORTA: Efficient Video Diffusion via Routing Sparse Attention
by: Sun, Wenhao, et al.
Published: (2025)

ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification
by: He, Yefei, et al.
Published: (2024)

Occupancy as Set of Points
by: Shi, Yiang, et al.
Published: (2024)

Fast High Dynamic Range Radiance Fields for Dynamic Scenes
by: Wu, Guanjun, et al.
Published: (2024)

Youtu-VL: Unleashing Visual Potential via Unified Vision-Language Supervision
by: Wei, Zhixiang, et al.
Published: (2026)

ImageRef-VL: Enabling Contextual Image Referencing in Vision-Language Models
by: Yi, Jingwei, et al.
Published: (2025)