6 papers
A Visual Dependence-Aware Framework for Multimodal Unsupervised Continual Post-Training
Kaichen Li, Zhilin Zhu, Jianhao Huang +7
In this paper, we explore a novel task of Multimodal Unsupervised Continual Post-Training (MU-CPT), enabling deployed MLLMs to continually evolve from streaming unlabeled data. Exi…
AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models
Zibo Shao, Baochen Xiong, Chengdong Xu +6
Agentic multimodal large language models (MLLMs) extend multimodal perception and reasoning with planning, tool use, and interaction in dynamic environments. Yet current models are…
Preference-Driven Online Adaptation for Personalized Interaction Initiation in Proactive AI Assistants
Yufeng Wang, Wei Zhang, Zhiquan Wen +5
AI assistants are typically reactive, relying on users to initiate interactions. Proactive assistants go beyond this paradigm by autonomously initiating interactions based on users…
A Survey on the Green Development of Large Models: From Resource-Efficient Architectures to Hardware-Software Co-Design
Linhui Xiao, Guiping Cao, Mingyue Guo +6
The rapid expansion of large-scale AI models has led to significant performance breakthroughs across diverse domains, yet it has also raised critical concerns regarding computation…
BARE: Towards Bias-Aware and Reasoning-Enhanced One-Tower Visual Grounding
Hongbing Li, Linhui Xiao, Zihan Zhao +4
Visual Grounding (VG), which aims to locate a specific region referred to by expressions, is a fundamental yet challenging task in the multimodal understanding fields. While recent…
OneRef: Unified One-tower Expression Grounding and Segmentation with Mask Referring Modeling
Linhui Xiao, Xiaoshan Yang, Fang Peng +2
Constrained by the separate encoding of vision and language, existing grounding and referring segmentation works heavily rely on bulky Transformer-based fusion en-/decoders and a v…