Search papers, labs, and topics across Lattice.
Affiliation:
4
0
7
Auxiliary views can enhance LLM learning efficiency, revealing that reallocation of training tokens can lead to better factual recall even when using weaker teacher models.
Penalizing shifts in safety representations during reasoning fine-tuning can restore LLM safety without sacrificing performance, revealing a critical interplay between reasoning and safety in model training.
Scattering-aware feature decomposition boosts few-shot SAR object detection performance by effectively leveraging sensor-specific characteristics.
System prompts in commercial AI products are often a mixed bag, with 40% harboring instructions that can undermine user interests, revealing a critical gap in accountability.
