Search papers, labs, and topics across Lattice.
Tencent Technology
3
0
7
4
Forget sifting through walls of text – now you can pinpoint exactly where the AI found its answer, down to the pixel, even in complex visuals like charts and diagrams.
Parameter importance isn't forever: dynamically adapting which parameters are frozen during fine-tuning significantly improves generalization and reduces forgetting in LLMs.
Safety-aligned LLMs are so consistently risk-averse that a single, transferable "poison" document can now block up to 96% of queries across different RAG systems, even without access to the target model.
