Search papers, labs, and topics across Lattice.
National Anti-Counterfeit Engineering Research Center, Huazhong University of Science and Technology, V generation refers to text-and-image-to-video generation, where both text and image prompts are used as inputs.
3
0
6
Recommender systems can move beyond passive item lists: RecPilot's multi-agent framework autonomously explores item spaces and generates user-centric reports, significantly reducing user effort in item evaluation.
Image-to-video models can be jailbroken by hiding malicious instructions in seemingly harmless reference images, achieving an 83.5% attack success rate on commercial systems.
LLMs learn to recommend better by looking inside themselves, using intermediate layer activations to generate harder negatives on the fly.
