collaborators

6 papers

cs.CV2026

From Pixels to Words -- Towards Native One-Vision Models at Scale

Haiwen Diao, Jiahao Wang, Penghao Wu +18

Current vision-language models (VLMs) typically stitch together separate image encoders and language decoders via multi-stage alignment, a modular framework that inevitably fragmen…

cs.CV2025

Visual Jigsaw Post-Training Improves MLLMs

Penghao Wu, Yushan Zhang, Haiwen Diao +3

Reinforcement learning based post-training has recently emerged as a powerful paradigm for enhancing the alignment and reasoning capabilities of multimodal large language models (M…

cs.CV2025

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,…

cs.AI2025

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior

Penghao Wu, Shengnan Ma, Bo Wang +3

Multimodal Large Language Models (MLLMs) have shown great potential in revolutionizing Graphical User Interface (GUI) automation. However, existing GUI models mostly rely on learni…

cs.CV2025

Streamline Without Sacrifice -- Squeeze out Computation Redundancy in LMM

Penghao Wu, Lewei Lu, Ziwei Liu

Large multimodal models excel in multimodal tasks but face significant computational challenges due to excessive computation on visual tokens. Unlike token reduction methods that f…

cs.CV2025

Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos

Kairui Hu, Penghao Wu, Fanyi Pu +5

Humans acquire knowledge through three cognitive stages: perceiving information, comprehending knowledge, and adapting knowledge to solve novel problems. Videos serve as an effecti…