Search papers, labs, and topics across Lattice.
6
0
8
Disagreement among verifiers can be a powerful signal for identifying errors in multimodal reasoning, leading to a 5.95% performance boost without any training.
Abstaining from uncertain predictions can enhance LLM accuracy in medical applications by 9.6 percentage points, transforming uncertainty into a strategic advantage.
Achieving a variance reduction in TensorSketch without sacrificing input-sparsity efficiency could revolutionize high-dimensional data processing.
Privacy and accuracy can be complementary in federated fine-tuning, with FedChronos achieving a 31% improvement in forecasting accuracy while ensuring data privacy.
Current user modeling benchmarks are child's play compared to the real-world challenges exposed by HORIZON, a massive new dataset spanning 54M users and diverse domains.
LLMs can reason more causally by simply checking if their counterfactual predictions are consistent, even without any extra training data.
