5 papers
Adaptive Moments are Surprisingly Effective for Plug-and-Play Diffusion Sampling
Christian Belardi, Justin Lovelace, Kilian Q. Weinberger +1
Guided diffusion sampling relies on approximating often intractable likelihood scores, which introduces significant noise into the sampling dynamics. We propose using adaptive mome…
Learning from Synthetic Data Improves Multi-hop Reasoning
Anmol Kabra, Yilun Yin, Albert Gong +6
Reinforcement Learning (RL) has been shown to significantly boost reasoning capabilities of large language models (LLMs) in math, coding, and multi-hop reasoning tasks. However, RL…
Improving Multislice Electron Ptychography with a Generative Prior
Christian K. Belardi, Chia-Hao Lee, Yingheng Wang +4
Multislice electron ptychography (MEP) is an inverse imaging technique that computationally reconstructs the highest-resolution images of atomic crystal structures from diffraction…
PhantomWiki: On-Demand Datasets for Reasoning and Retrieval Evaluation
Albert Gong, KamilÄ StankeviÄiÅ«tÄ, Chao Wan +6
High-quality benchmarks are essential for evaluating reasoning and retrieval capabilities of large language models (LLMs). However, curating datasets for this purpose is not a perm…
On Speeding Up Language Model Evaluation
Jin Peng Zhou, Christian K. Belardi, Ruihan Wu +4
Developing prompt-based methods with Large Language Models (LLMs) requires making numerous decisions, which give rise to a combinatorial search problem over hyper-parameters. This…