8 papers
ParVL: Parallel Scaling and Expandable Compute Allocation for Multimodal LLMs
Yang Yang, Qinyu Zhao, Mouxiang Chen +5
Existing scaling strategies for Multimodal Large Language Models (MLLMs) typically expand either model parameters or sequential inference computation, incurring substantial memory…
Thinking Without Images: Internalizing Visual Manipulation with On-Policy Self-Distillation
Yishuo Cai, Jiahui Liu, Yuanxin Liu +9
''Thinking with Images'' has emerged as an effective paradigm for fine-grained visual reasoning: by explicitly zooming into relevant regions and reasoning over crops, models can ac…
StableI2I: Spotting Unintended Changes in Image-to-Image Transition
Jiayang Li, Shuo Cao, Xiaohui Li +6
In most real-world image-to-image (I2I) scenarios, existing evaluations primarily focus on instruction following and the perceptual quality or aesthetics of the generated images. H…
Accelerating Masked Image Generation by Learning Latent Controlled Dynamics
Kaiwen Zhu, Quansheng Zeng, Yuandong Pu +8
Masked Image Generation Models (MIGMs) have achieved great success, yet their efficiency is hampered by the multiple steps of bi-directional attention. In fact, there exists notabl…
UniPercept: Towards Unified Perceptual-Level Image Understanding across Aesthetics, Quality, Structure, and Texture
Shuo Cao, Jiayang Li, Xiaohui Li +12
Multimodal large language models (MLLMs) have achieved remarkable progress in visual understanding tasks such as visual grounding, segmentation, and captioning. However, their abil…
ArtiMuse: Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level Understanding
Shuo Cao, Nan Ma, Jiayang Li +12
The rapid advancement of educational applications, artistic creation, and AI-generated content (AIGC) technologies has substantially increased practical requirements for comprehens…