9 papers
V-Rubrics: Visual Faithfulness via Rubric-Based Reinforcement Learning
Shulin Tian, Minglun Li, Yuhao Dong +6
Vision-language models can produce fluent answers that are insufficiently grounded in the visual evidence: a single unsupported object, chart value, or intermediate inference can u…
Open Evaluation Agent: Efficient and Promptable Evaluation of Visual Generative Models
Shulin Tian, Ziqi Huang, Fan Zhang +3
Recent advances in visual generative models have enabled high-quality image and video generation, but evaluating these models often demands sampling hundreds or thousands of images…
SocialCoach: Personalized Social Skill Learning with Agentic Tutoring and Practice
Tianfu Wang, Max Xiong, Jianxun Lian +9
Social skills such as negotiation and leadership are crucial for personal and professional success in today's interconnected world. However, scalable and effective training remains…
TorchUMM: A Unified Multimodal Model Codebase for Evaluation, Analysis, and Post-training
Yinyi Luo, Wenwen Wang, Hayes Bai +6
Recent advances in unified multimodal models (UMMs) have led to a proliferation of architectures capable of understanding, generating, and editing across visual and textual modalit…
Beyond Voxel 3D Editing: Learning from 3D Masks and Self-Constructed Data
Yizhao Xu, Hongyuan Zhu, Caiyun Liu +6
3D editing refers to the ability to apply local or global modifications to 3D assets. Effective 3D editing requires maintaining semantic consistency by performing localized changes…
EvoDesign: Agentic Editable Diagram Creation via Design Expertise Evolution
Tianfu Wang, Leilei Ding, Ziyang Tao +15
High-fidelity diagram creation requires coordinated visual-spatial decisions over semantic topology, visual styling, and geometric layout. Existing methods face a representation ga…
PromptFlow: Training Prompts Like Neural Networks
Jingyi Wang, Hongyuan Zhu, Ye Niu +1
Large Language Models (LLMs) have demonstrated profound impact on Natural Language Processing (NLP) tasks. However, their effective deployment across diverse domains often require…
Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning
Shulin Tian, Ruiqi Wang, Hongming Guo +7
We introduce Ego-R1, a novel framework for reasoning over ultra-long (i.e., in days and weeks) egocentric videos, which leverages a structured Chain-of-Tool-Thought (CoTT) process,…
Synergistic Dual Spatial-aware Generation of Image-to-Text and Text-to-Image
Yu Zhao, Hao Fei, Xiangtai Li +6
In the visual spatial understanding (VSU) area, spatial image-to-text (SI2T) and spatial text-to-image (ST2I) are two fundamental tasks that appear in dual form. Existing methods f…