activity
20232026
most citedInternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks

17 citations · 74 across the 37 of their papers we have counts for

collaborators
Showing cs.CVShow all

43 papers · 1 filter

cs.CV2026

ParVL: Parallel Scaling and Expandable Compute Allocation for Multimodal LLMs

Yang Yang, Qinyu Zhao, Mouxiang Chen +5

Existing scaling strategies for Multimodal Large Language Models (MLLMs) typically expand either model parameters or sequential inference computation, incurring substantial memory…

cs.CV2026

HSD: Training-Free Acceleration for Document Parsing Vision-Language Models with Hierarchical Speculative Decoding

Wenhui Liao, Hongliang Li, Pengyu Xie +15

Document parsing is a fundamental task in multimodal understanding, supporting a wide range of downstream applications such as information extraction and intelligent document analy…

cs.CV2025

MetaCaptioner: Towards Generalist Visual Captioning with Open-source Suites

Zhenxin Lei, Zhangwei Gao, Changyao Tian +12

Generalist visual captioning goes beyond a simple appearance description task, but requires integrating a series of visual cues into a caption and handling various visual domains.…

cs.CV2025

NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints

Changyao Tian, Hao Li, Gen Luo +11

Compositional training has been the de-facto paradigm in existing Multimodal Large Language Models (MLLMs), where pre-trained vision encoders are connected with pre-trained LLMs th…

cs.CV2025

ViCO: A Training Strategy towards Semantic Aware Dynamic High-Resolution

Long Cui, Weiyun Wang, Jie Shao +6

Existing Multimodal Large Language Models (MLLMs) suffer from increased inference costs due to the additional vision tokens introduced by image inputs. In this work, we propose Vis…

cs.CV2025

InternSVG: Towards Unified SVG Tasks with Multimodal Large Language Models

Haomin Wang, Jinhui Yin, Qi Wei +12

General SVG modeling remains challenging due to fragmented datasets, limited transferability of methods across tasks, and the difficulty of handling structural complexity. In respo…