8 papers
Pay More Attention To Text In High-Resolution MLLMs
Zhongkuan Mao, Wenzhuo Zhao, Xianjie Liu +7
Failures of high-resolution MLLMs are commonly attributed to a visual problem, motivating zooming, cropping, and related visual interventions to recover fine-grained evidence or su…
Transferring the Intelligence of VLMs to Robotic Control
Meng-Hao Guo, Zhe-Han Mo, Jia-Jun Wang +6
Humans can seamlessly adapt to both physical and digital worlds, suggesting that while a digital-to-real gap exists in embodiment, environment and task, human intelligence itself m…
SEER: Long-Context Reasoning via Selective Visual-Text Compression
Jiawei Xu, Zhilin Zhai, Jinrui Fang +6
Long-context reasoning remains computationally expensive for large language models due to the quadratic complexity of attention over text tokens. Visual-text compression offers a p…
Thinking Once Is Enough: Intermediate-Layer Evidence Routing for High-Resolution VQA
Zhongkuan Mao, Xianjie Liu, Tianyu Meng +9
High-resolution visual question answering (HR-VQA) is often treated as a problem of insufficient evidence acquisition, where failing multimodal large language models must inspect i…
GeoTikzBridge: Advancing Multimodal Code Generation for Geometric Perception and Reasoning
Jiayin Sun, Caixia Sun, Boyu Yang +7
Multimodal Large Language Models (MLLMs) have recently demonstrated remarkable perceptual and reasoning abilities. However, they struggle to perceive fine-grained geometric structu…
Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMs
Yi Zhang, Bolin Ni, Xin-Sheng Chen +7
Fully open multimodal large language models (MLLMs) currently lag behind proprietary counterparts, primarily due to a significant gap in data quality for supervised fine-tuning (SF…
RBench-V: A Primary Assessment for Visual Reasoning Models with Multi-modal Outputs
Meng-Hao Guo, Xuanyu Chu, Qianrui Yang +12
The rapid advancement of native multi-modal models and omni-models, exemplified by GPT-4o, Gemini, and o3, with their capability to process and generate content across modalities s…
R-Bench: Graduate-level Multi-disciplinary Benchmarks for LLM & MLLM Complex Reasoning Evaluation
Meng-Hao Guo, Jiajun Xu, Yi Zhang +14
Reasoning stands as a cornerstone of intelligence, enabling the synthesis of existing knowledge to solve complex problems. Despite remarkable progress, existing reasoning benchmark…