Search papers, labs, and topics across Lattice.
6
0
11
23
Evolving adversarial strategies can achieve nearly 100% success against state-of-the-art LLMs while maintaining robust defenses that adapt in real-time.
DataShield reveals that aligning consensus subspaces across multiple LLMs can drastically enhance safety by filtering out risky fine-tuning data more effectively than previous methods.
Clinical agents face a staggering 62.3% accuracy ceiling in complex EHR reasoning, revealing significant gaps in current AI capabilities.
Spear accelerates the synthesis of optimal abstract transformers by exploiting parallelism, outperforming state-of-the-art solvers in both efficiency and scalability.
Stop retraining watermarks for every LoRA: LoRA-Key lets you inject a reusable, user-specific copyright key into text-to-image models without sacrificing image quality or style.
Forget broad brushstrokes: pinpointing and tweaking just 1% of an LLM's weights can slash attack success rates by over 50% or preserve safety during fine-tuning.
