From the 1 of 6 linked papers with an AI index.
6 papers
ObjectStream: Latent Objects as Memory Anchors for Streaming Video Understanding
Mingkang Dong, Muxin Pu, Jie Li +8
ObjectStream introduces a training‑free method that extracts latent objects from frozen Video‑LLM representations and uses them as persistent memory anchors to improve streaming vi…
Pistachio: Towards Synthetic, Balanced, and Long-Form Video Anomaly Benchmarks
Jie Li, Hongyi Cai, Mingkang Dong +4
Automatically detecting abnormal events in videos is crucial for modern autonomous systems, yet existing Video Anomaly Detection (VAD) benchmarks lack the scene diversity, balanced…
VisNec: Measuring and Leveraging Visual Necessity for Multimodal Instruction Tuning
Mingkang Dong, Hongyi Cai, Jie Li +4
The effectiveness of multimodal instruction tuning depends not only on dataset scale, but critically on whether training samples genuinely require visual reasoning. However, existi…
Once-For-All: A Train-Once and Select-Anytime Framework for Multimodal Instruction Tuning
Mingkang Dong, Hongyi Cai, Xiwen Lei +3
Multimodal instruction tuning is the de facto recipe for adapting vision language models (VLMs), yet instruction data are highly redundant, making data selection critical for train…
Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model
Tao Lin, Yuxin Du, Jiting Liu +14
Vision-Language-Action models have emerged as a promising paradigm for robotic manipulation by unifying perception, language grounding, and action generation. However, they often s…
AutoDebias: Automated Framework for Debiasing Text-to-Image Models
Hongyi Cai, Mohammad Mahdinur Rahman, Mingkang Dong +7
Text-to-Image (T2I) models generate high-quality images but are vulnerable to malicious backdoor attacks that inject harmful biases (e.g., trigger-activated gender or racial stereo…