HRScene: How Far Are VLMs from Effective High-Resolution Image Understanding? "we introduce HRScene, a novel unified benchmark for HRI understanding with rich scenes. HRScene incorporates 25 real-world datasets and 2 synthetic diagnostic datasets with resolutions ranging from

📢 New paper! FoVer enhances PRMs for step-level verification of LLM reasoning w/o human annotation 🚀 We synthesize training data using formal verification tools and improve LLMs at step-level verification of LLM responses on MATH, AIME, MMLU, BBH, etc. arxiv.org/abs/2505.15960

Vision Language Models display a peculiar blind spot: their ability to process image content declines in a U-shaped pattern based on Manhattan distance from corners, suggesting fundamental limitations in handling high-resolution layouts.

HRScene got accepted at #ICCV2025! HRScene is a novel unified benchmark for high-resolution image understanding with 25 scenes and 2 NIAH tests. Home page: yszh8.github.io/hrscene/ (Sorry, EvalAI for submission does not work currently...) My PhD research began with long text

Our paper VisOnlyQA has been accepted to Conference on Language Modeling #COLM2025! See you in Montreal🍁 We find that even recent Vision Language Models struggle with simple questions about geometric properties in images, such as "What is the degree of angle AOD?"🧐 arxiv.org/abs/2412.00947

We updated our VisOnlyQA paper for #COLM2025! * LVLMs exhibit weak geometric perception even on geometric shapes with 2–3 lines 😭 * Gemini 2.5 Pro largely improves over prior models on charts and chemistry 😳 but still struggles with geometric shapes 😖 arxiv.org/abs/2412.00947

How are researchers optimizing AI systems for science? CSRAI Affiliate Rui Zhang from Penn State EECS shares how to improve the efficiency and usefulness of AI and some strategies individuals can employ to get more value out of their personal AI use. psu.edu/news/engineeri…

📢 Call for Papers: NewSumm 2025 - The 5th New Frontiers in Summarization Workshop at EMNLP 2025 The summarization research community is invited to submit to NewSumm 2025, co-located with EMNLP 2025! As LLMs continue to transform our field, we're expanding beyond traditional

I’ve completed my Ph.D. Yale Engineering and will be joining Stanford University as a postdoc! 1/n

We are excited to announce WMAC 2026, co-located with AAAI 2026!

I'll be attending #COLM2025 Conference on Language Modeling in person 🇨🇦 I will present our work, VisOnlyQA, on the limitations of vision-language models at Poster Session 4 (Wed). Looking forward to chatting with everyone! Paper: openreview.net/forum?id=PYHwl… x.com/RyoKamoi/statu…