2 citations · 3 across the 13 of their papers we have counts for
14 papers
How Much Parallelism Is "Free"? A Principle of Near-Free Parallelism for Parallel Decoding
Minghua He, Lingzhe Zhang, Yuan Liu +2
Parallel decoding improves generation efficiency by processing multiple decode positions within a single decode forward, but reported speedups conflate algorithmic token utilizatio…
DiffSpot: Can VLMs Spot Fine-Grained Visual Differences in Web Interfaces?
Linhao Zhang, Aiwei Liu, Yuan Liu +1
Vision-language models (VLMs) have made strong progress on high-level image-text alignment, yet their ability to perceive subtle visual differences remains limited. We study this p…
POINTS-Seeker: An Open Recipe for Multimodal Search Agents with Visual Memory Management
Yikun Liu, Yuan Liu, Haicheng Wang +6
Large Multimodal Models (LMMs) excel at visual perception but struggle with real-time, knowledge-intensive queries due to their reliance on static parametric knowledge. While multi…
VersaViT: Enhancing MLLM Vision Backbones via Task-Guided Optimization
Yikun Liu, Yuan Liu, Shangzhe Di +8
Multimodal Large Language Models (MLLMs) have recently achieved remarkable success in visual-language understanding, demonstrating superior high-level semantic alignment within the…
POINTS-GUI-G: GUI-Grounding Journey
Zhongyin Zhao, Yuan Liu, Yikun Liu +7
The rapid advancement of vision-language models has catalyzed the emergence of GUI agents, which hold immense potential for automating complex tasks, from online shopping to flight…
ERNIE 5.0 Technical Report
Haifeng Wang, Hua Wu, Tian Wu +432
In this report, we introduce ERNIE 5.0, a natively autoregressive foundation model desinged for unified multimodal understanding and generation across text, image, video, and audio…
FinMMDocR: Benchmarking Financial Multimodal Reasoning with Scenario Awareness, Document Understanding, and Multi-Step Computation
Zichen Tang, Haihong E, Rongjin Li +18
We introduce FinMMDocR, a novel bilingual multimodal benchmark for evaluating multimodal large language models (MLLMs) on real-world financial numerical reasoning. Compared to exis…
Zero-Training Task-Specific Model Synthesis for Few-Shot Medical Image Classification
Yao Qin, Yangyang Yan, YuanChao Yang +4
Deep learning models have achieved remarkable success in medical image analysis but are fundamentally constrained by the requirement for large-scale, meticulously annotated dataset…
Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs
Yongyi Su, Haojie Zhang, Shijie Li +11
Multimodal large language models (MLLMs) have advanced rapidly in recent years. However, existing approaches for vision tasks often rely on indirect representations, such as genera…
BigBang-Proton Technical Report: Next-Word-Prediction is Scientific Multitask Learner
Hengkui Wu, Liujiang Liu, Jihua He +23
We introduce BigBang-Proton, a unified sequence-based architecture for auto-regressive language modeling pretrained on cross-scale, cross-structure, cross-discipline real-world sci…
POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion
Yuan Liu, Zhongyin Zhao, Le Tian +8
High-quality labeled data is essential for training accurate document conversion models, particularly in domains with complex formats such as tables, formulas, and multi-column tex…
POINTS1.5: Building a Vision-Language Model towards Real World Applications
Yuan Liu, Le Tian, Xiao Zhou +4
Vision-language models have made significant strides recently, demonstrating superior performance across a range of tasks, e.g. optical character recognition and complex diagram an…
POINTS: Improving Your Vision-language Model with Affordable Strategies
Yuan Liu, Zhongyin Zhao, Ziyuan Zhuang +3
In recent years, vision-language models have made significant strides, excelling in tasks like optical character recognition and geometric problem-solving. However, several critica…
Rethinking Overlooked Aspects in Vision-Language Models
Yuan Liu, Le Tian, Xiao Zhou +1
Recent advancements in large vision-language models (LVLMs), such as GPT4-V and LLaVA, have been substantial. LLaVA's modular architecture, in particular, offers a blend of simplic…