9 papers · 1 filter
ViMU: Benchmarking Video Metaphorical Understanding
Qi Li, Xinchao Wang
Any new medium, once it emerges, is used for more than the transmission of overt content alone. The information it carries typically operates on two levels: one is the content dire…
Gated Condition Injection without Multimodal Attention: Towards Controllable Linear-Attention Transformers
Yuhe Liu, Zhenxiong Tan, Yujia Hu +2
Recent advances in diffusion-based controllable visual generation have led to remarkable improvements in image quality. However, these powerful models are typically deployed on clo…
Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models
Lexiang Xiong, Qi Li, Jingwen Ye +1
Vision-Language Models (VLMs) frequently "hallucinate" - generate plausible yet factually incorrect statements - posing a critical barrier to their trustworthy deployment. In this…
ViFeEdit: A Video-Free Tuner of Your Video Diffusion Transformer
Ruonan Yu, Zhenxiong Tan, Zigeng Chen +2
Diffusion Transformers (DiTs) have demonstrated remarkable scalability and quality in image and video generation, prompting growing interest in extending them to controllable gener…
Sponge Tool Attack: Stealthy Denial-of-Efficiency against Tool-Augmented Agentic Reasoning
Qi Li, Xinchao Wang
Enabling large language models (LLMs) to solve complex reasoning tasks is a key step toward artificial general intelligence. Recent work augments LLMs with external tools to enable…
Vid-SME: Membership Inference Attacks against Large Video Understanding Models
Qi Li, Runpeng Yu, Xinchao Wang
Multimodal large language models (MLLMs) demonstrate remarkable capabilities in handling complex multimodal tasks and are increasingly adopted in video understanding applications.…
Dimple: Discrete Diffusion Multimodal Large Language Model with Parallel Decoding
Runpeng Yu, Xinyin Ma, Xinchao Wang
In this work, we propose Dimple, the first Discrete Diffusion Multimodal Large Language Model (DMLLM). We observe that training with a purely discrete diffusion approach leads to s…
Introducing Visual Perception Token into Multimodal Large Language Model
Runpeng Yu, Xinyin Ma, Xinchao Wang
To utilize visual information, Multimodal Large Language Model (MLLM) relies on the perception process of its vision encoder. The completeness and accuracy of visual perception sig…
Neural Lineage
Runpeng Yu, Xinchao Wang
Given a well-behaved neural network, is possible to identify its parent, based on which it was tuned? In this paper, we introduce a novel task known as neural lineage detection, ai…