5 papers
Recursive Self-Improvement in Unified Multimodal Models
Huijuan Wang, Chufan Shi, Cheng Yang +3
Unified multimodal models (UMMs) understand and generate both text and images, which lets a model produce its own training data. Existing self-improvement in UMMs keeps supervision…
UReason: Benchmarking Reasoning-to-Generation Alignment in Unified Multimodal Models
Cheng Yang, Chufan Shi, Bo Shui +7
Unified multimodal models (UMMs) aim to integrate multimodal understanding and generation within a unified architecture, yet it remains unclear to what extent textual and visual mo…
Optical Context Compression Is Just (Bad) Autoencoding
Ivan Yee Lee, Cheng Yang, Taylor Berg-Kirkpatrick
DeepSeek-OCR shows that rendered text can be reconstructed from a small number of vision tokens, sparking excitement about using vision as a compression medium for long textual con…
Structured Relational Reasoning for Group Activity Assessment
Thinesh Thiyakesan Ponbagavathi, Chengzheng Yang, Alina Roitberg
Group Activity Detection (GAD) involves recognizing social groups and their collective behaviors in videos. Vision Foundation Models (VFMs), like DINOv2, offer excellent features b…
Improving Vision-and-Language Reasoning via Spatial Relations Modeling
Cheng Yang, Rui Xu, Ye Guo +5
Visual commonsense reasoning (VCR) is a challenging multi-modal task, which requires high-level cognition and commonsense reasoning ability about the real world. In recent years, l…