51 papers
V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failure
Zhetong Zhang, Honghao Fu, Miao Xu +2
As Video Large Language Models are increasingly deployed in real-world applications, ensuring their safety alignment has become critical. Counterintuitively, we find that harmful v…
EchoFoley: Event-Centric Hierarchical Control for Video Grounded Creative Sound Generation
Bingxuan Li, Yiming Cui, Yicheng He +4
Sound effects build an essential layer of multimodal storytelling, shaping the emotional atmosphere and the narrative semantics of videos. Despite recent advancement in video-text-…
What Should a Streaming Video Model Remember?
Haonan Ge, Yiwei Wang, Hang Wu +1
Streaming video understanding models must answer queries at any moment during an ongoing stream, using only what they have observed so far and under fixed memory and computation bu…
Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning
Zhicheng Yang, Zhijiang Guo, Yifan Song +5
On-policy distillation (OPD) leverages dense teacher rewards to enhance reasoning models. However, scaling OPD to long-horizon tasks exposes a critical flaw: as the student's gener…
Semantic-Aware Adaptive Visual Memory for Streaming Video Understanding
Hang Wu, Sherin Mary Mathews, Yujun Cai +2
Online streaming video understanding requires models to process continuous visual inputs and respond to user queries in real time, where the unbounded stream and unpredictable quer…
Hard to Read, Easy to Jailbreak: How Visual Degradation Bypasses MLLM Safety Alignment
Zhixue Song, Boyan Han, Yiwei Wang +1
Recent advancements in visual context compression enable MLLMs to process ultra-long contexts efficiently by rendering text into images. However, we identify a critical vulnerabili…