6 papers
Look on Demand: A Cognitive Scheduling Framework for Visual Evidence Acquisition in Multimodal Reasoning
Yang Zhang, Xiaoshuai Sun, Rui Zhao +5
Existing multimodal reasoning approaches predominantly follow two paradigms: converting visual inputs into text prior to reasoning, or performing end-to-end reasoning within a unif…
FlowInOne:Unifying Multimodal Generation as Image-in, Image-out Flow Matching
Junchao Yi, Rui Zhao, Jiahao Tang +7
Multimodal generation has long been dominated by text-driven pipelines where language dictates vision but cannot reason or create within it. We challenge this paradigm by asking wh…
VIDEOP2R: Video Understanding from Perception to Reasoning
Yifan Jiang, Yueying Wang, Rui Zhao +4
Reinforcement fine-tuning (RFT), a two-stage framework consisting of supervised fine-tuning (SFT) and reinforcement learning (RL) has shown promising results on improving reasoning…
Perceptio: Perception Enhanced Vision Language Models via Spatial Token Generation
Yuchen Li, Amanmeet Garg, Shalini Chaudhuri +2
Large Vision Language Models (LVLMs) excel at semantic understanding but struggle with fine grained spatial grounding, as the model must implicitly infer complex geometry without e…
What Happens Next? Next Scene Prediction with a Unified Video Model
Xinjie Li, Zhimin Chen, Rui Zhao +3
Recent unified models for joint understanding and generation have significantly advanced visual generation capabilities. However, their focus on conventional tasks like text-to-vid…
Causal Reasoning Elicits Controllable 3D Scene Generation
Shen Chen, Ruiyu Zhao, Jiale Zhou +3
Existing 3D scene generation methods often struggle to model the complex logical dependencies and physical constraints between objects, limiting their ability to adapt to dynamic a…