Search papers, labs, and topics across Lattice.
脡cole polytechnique, Institut Polytechnique de Paris
2
0
6
Prompt injection defenses can degrade LLM agent utility by altering benign behavior; RAISED achieves robustness without this cost through self-distillation on generated scenarios.
Forget rule-based generation: contrastive learning unlocks a new level of realism in tampered document image generation, boosting model performance on real-world data.
