5 papers
DIVA: Exploiting Cross-Step Conditional Propagation for Visual Jailbreaks in Discrete Diffusion Vision-Language Models
Guorui Song, Runqing Tang, Jingye Zhang +11
Large vision-language models (VLMs) are increasingly deployed in safety-critical settings, yet existing visual jailbreak research has focused almost exclusively on autoregressive a…
OraclePhys: A Systematic Framework for LLM Fine-Tuning on Structural Mechanics
Mingyu Li, Guorui Song, Jing Lin +1
What a language model internalizes from fine-tuning is usually diagnosed after the fact. We make it an experimental variable. OraclePhys is a systematic fine-tuning framework with…
UniMo: Unified Motion Generation and Understanding with Chain of Thought
Guocun Wang, Kenkun Liu, Jing Lin +3
Existing 3D human motion generation and understanding methods often exhibit limited interpretability, restricting effective mutual enhancement between these inherently related task…
Towards Fine-Grained Human Motion Video Captioning
Guorui Song, Guocun Wang, Zhe Huang +4
Generating accurate descriptions of human actions in videos remains a challenging task for video captioning models. Existing approaches often struggle to capture fine-grained motio…
The Quest for Generalizable Motion Generation: Data, Model, and Evaluation
Jing Lin, Ruisi Wang, Junzhe Lu +10
Despite recent advances in 3D human motion generation (MoGen) on standard benchmarks, existing text-to-motion models still face a fundamental bottleneck in their generalization cap…