Energy
Latent Neural Operator for Solving Forward and Inverse PDE Problems
Corresponding Author.This work is supported by Beijing Municipal Science and Technology Project (No.
SciCode: A Research Coding Benchmark Curated by Scientists
Because LMs now surpass the performance of most humans except domain experts, evaluating them becomes increasingly challenging.
Advancing Spiking Neural Networks for Sequential Modeling with Central Pattern Generators
Spiking neural networks (SNNs) represent a promising approach to developing artificial neural networks that are both energy-efficient and biologically plausible.
QA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content Joรฃo Monteiro,3, Pierre-Andrรฉ Noรซl
Consequently, evaluating models on test splits that might have leaked into the training set is prone to misleading conclusions.
Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion
Work done as a visiting student at MIT. 38th Conference on Neural Information Processing Systems (NeurIPS 2024).
On conditional diffusion models for PDE simulations
In particular, we focus on diffusion models that are either trained in a conditional manner, or conditioned after unconditional training.