8 papers
CoSec: Benchmarking Agent Security in Communities
Hao Chen, Wenhui Dong, Ye Chen +12
LLM agents operate in persistent collaborative environments involving multiple users, communities, memories, files, and tools. Community boundaries may remain fixed or evolve with…
TOBench: A Task-Oriented Omni-Modal Benchmark for Real-World Tool-Using Agents
Zhiqiang Liu, Wenhui Dong, Yilang Tan +3
Tool-using agents are increasingly expected to operate across realistic professional workflows, where they must interpret multimodal inputs, coordinate external tools, inspect inte…
NGM: A Plug-and-Play Training-Free Memory Module for LLMs
Yuwen Qu, Wenhui Dong, Chenyang Si +3
Recent studies have introduced memory-augmented architectures that decouple knowledge storage from neural computation, enabling more direct access to stored representations. Howeve…
SpineBench: A Clinically Salient, Level-Aware Benchmark Powered by the SpineMed-450k Corpus
Ming Zhao, Wenhui Dong, Yang Zhang +23
Spine disorders affect 619 million people globally and are a leading cause of disability, yet AI-assisted diagnosis remains limited by the lack of level-aware, multimodal datasets.…
Small-Large Collaboration: Training-efficient Concept Personalization for Large VLM using a Meta Personalized Small VLM
Sihan Yang, Huitong Ji, Shaolin Lu +6
Personalizing Vision-Language Models (VLMs) to transform them into daily assistants has emerged as a trending research direction. However, leading companies like OpenAI continue to…
Ivy-Fake: A Unified Explainable Framework and Benchmark for Image and Video AIGC Detection
Changjiang Jiang, Wenhui Dong, Zhonghao Zhang +8
The rapid development of Artificial Intelligence Generated Content (AIGC) techniques has enabled the creation of high-quality synthetic content, but it also raises significant secu…
FiLA-Video: Spatio-Temporal Compression for Fine-Grained Long Video Understanding
Yanan Guo, Wenhui Dong, Jun Song +7
Recent advancements in video understanding within visual large language models (VLLMs) have led to notable progress. However, the complexity of video data and contextual processing…
FILA: Fine-Grained Vision Language Models
Shiding Zhu, Wenhui Dong, Jun Song +3
Recently, there has been growing interest in the capability of multimodal large language models (MLLMs) to process high-resolution images. A common approach currently involves dyna…