12 papers
Towards Communication-Efficient Social Intelligence in Language Agents
Linxiao Gong, Yijie Xu, Tianfu Wang +7
Socially intelligent language agents must negotiate, coordinate, and resolve conflicting preferences while respecting the time and attention of both participants. Balancing these d…
Unsupervised Post-Training of Foundation Models: A Survey
Yijie Xu, Qianyi Cai, Huizai Yao +9
Foundation-model post-training usually relies on human labels, preference data, stronger teachers, or executable verifiers. We study Unsupervised Post-Training (UPT): update-bearin…
SafeBuild-Bench: A Temporal-Robust Construction Safety Benchmark with Graph-Enhanced Data Mining
Yi Cui, Zilin Wang, Yijie Xu +5
Construction-safety models must handle concrete deployment risks, such as a worker standing near a scaffold edge without guardrails, rather than only recognize common objects in cu…
GATE-3D: Geometry-Aware Test-time Adaptive Reranking for Open-Set 3D Shape Retrieval
Hao Wu, Heyi Lin, Zilin Wang +3
Large pretrained vision models have substantially improved appearance-based 3D shape retrieval, but they still confuse shapes that look similar while differing in geometry. Althoug…
From Events to Clarity: The Event-Guided Diffusion Framework for Dehazing
Ling Wang, Yunfan Lu, Wenzong Ma +3
Clear imaging under hazy conditions is a critical task. Prior-based and neural methods have improved results. However, they operate on RGB frames, which suffer from limited dynamic…
Beyond Boundaries: Leveraging Vision Foundation Models for Source-Free Object Detection
Huizai Yao, Sicheng Zhao, Pengteng Li +6
Source-Free Object Detection (SFOD) aims to adapt a source-pretrained object detector to a target domain without access to source data. However, existing SFOD methods predominantly…
You only need 4 extra tokens: Synergistic Test-time Adaptation for LLMs
Yijie Xu, Huizai Yao, Zhiyu Guo +5
Large language models (LLMs) are increasingly deployed in specialized domains such as finance, medicine, and agriculture, where they face significant distribution shifts from their…
See&Trek: Training-Free Spatial Prompting for Multimodal Large Language Model
Pengteng Li, Pinhao Song, Wuyang Li +5
We introduce SEE&TREK, the first training-free prompting framework tailored to enhance the spatial understanding of Multimodal Large Language Models (MLLMS) under vision-only const…
DeblurSplat: SfM-free 3D Gaussian Splatting with Event Camera for Robust Deblurring
Pengteng Li, Yunfan Lu, Pinhao Song +4
In this paper, we propose the first Structure-from-Motion (SfM)-free deblurring 3D Gaussian Splatting method via event camera, dubbed DeblurSplat. We address the motion-deblurring…
From Events to Enhancement: A Survey on Event-Based Imaging Technologies
Yunfan Lu, Xiaogang Xu, Pengteng Li +4
Event cameras offering high dynamic range and low latency have emerged as disruptive technologies in imaging. Despite growing research on leveraging these benefits for different im…
SEE: See Everything Every Time -- Adaptive Brightness Adjustment for Broad Light Range Images via Events
Yunfan Lu, Xiaogang Xu, Hao Lu +8
Event cameras, with a high dynamic range exceeding , significantly outperform traditional embedded cameras, robustly recording detailed changing information under various li…
EventVL: Understand Event Streams via Multimodal Large Language Model
Pengteng Li, Yunfan Lu, Pinghao Song +3
The event-based Vision-Language Model (VLM) recently has made good progress for practical vision tasks. However, most of these works just utilize CLIP for focusing on traditional p…