collaborators

5 papers

cs.CR2026

Automated High-Precision Extraction and Forensic Verification of Data-Bearing Vector Figures

Bowen Sun, Chaowei Xiao

The quantitative record of science and engineering is increasingly carried by figures rather than text or tables, and a reader who needs the underlying numbers must usually re-digi…

cs.CR2026

TwinGate: Stateful Defense against Decompositional Jailbreaks in Untraceable Traffic via Asymmetric Contrastive Learning

Bowen Sun, Chaozhuo Li, Yaodong Yang +2

Decompositional jailbreaks pose a critical threat to large language models (LLMs) by allowing adversaries to fragment a malicious objective into a sequence of individually benign q…

cs.CV2026

CamReasoner: Reinforcing Camera Movement Understanding via Structured Spatial Reasoning

Hang Wu, Yujun Cai, Zehao Li +4

Understanding camera dynamics is a fundamental pillar of video spatial intelligence. However, existing multimodal models predominantly treat this task as a black-box classification…

cs.CV2026

PAS: A Training-Free Stabilizer for Temporal Encoding in Video LLMs

Bowen Sun, Yujun Cai, Ming-Hsuan Yang +2

Video LLMs suffer from temporal inconsistency: small shifts in frame timing can flip attention and suppress relevant frames. We trace this instability to the common extension of Ro…

cs.CL2025

Blockwise SFT for Diffusion Language Models: Reconciling Bidirectional Attention and Autoregressive Decoding

Bowen Sun, Yujun Cai, Ming-Hsuan Yang +1

Discrete diffusion language models have shown strong potential for text generation, yet standard supervised fine-tuning (SFT) misaligns with their semi-autoregressive inference: tr…