6 papers
OmniMapBench: Benchmarking Visual-Centric Reasoning on Diverse Map Documents
Yang Chen, Yunwen Li, Yufan Shen +6
Recent advancements in LVLMs necessitate robust benchmarks for complex, visually grounded reasoning. A critical limitation is identified in many document understanding benchmarks:…
Mamoda2.5: Enhancing Unified Multimodal Model with DiT-MoE
Yangming Shi, Shixiang Zhu, Tao Shen +14
We present Mamoda2.5, a unified AR-Diffusion framework that seamlessly integrates multimodal understanding and generation within a single architecture. To efficiently enhance the m…
Investigating Redundancy in Multimodal Large Language Models with Multiple Vision Encoders
Yizhou Wang, Song Mao, Yang Chen +8
Recent multimodal large language models (MLLMs) increasingly integrate multiple vision encoders to improve performance on various benchmarks, assuming that diverse pretraining obje…
IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video?
Yang Chen, Minghao Liu, Yufan Shen +18
The webpage-to-code task requires models to understand visual representations of webpages and generate corresponding code. However, existing benchmarks primarily focus on static sc…
Learning Only with Images: Visual Reinforcement Learning with Reasoning, Rendering, and Visual Feedback
Yang Chen, Yufan Shen, Wenxuan Huang +7
Multimodal Large Language Models (MLLMs) exhibit impressive performance across various visual tasks. Subsequent investigations into enhancing their visual reasoning abilities have…
QuaDMix: Quality-Diversity Balanced Data Selection for Efficient LLM Pretraining
Fengze Liu, Weidong Zhou, Binbin Liu +8
Quality and diversity are two critical metrics for the training data of large language models (LLMs), positively impacting performance. Existing studies often optimize these metric…