AutoML for neuromorphic computing and application-driven co-design: asynchronous, massively parallel optimization of spiking architectures

cuDNN: Efficient Primitives for Deep Learning

Chip Placement with Deep Reinforcement Learning

Good, I. J. (1966). Speculations concerning the first ultraintelligent machine. In Advances in computers (Vol. 6, pp. 31-88).

Improving Factuality and Reasoning in Language Models through Multiagent Debate

Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text | Journal of Artificial Intelligence Research

ORCa: Glossy Objects as Radiance Field Cameras

Learning to Generate Novel Scientific Directions with Contextualized Literature-based Discovery

Reverse Engineering Self-Supervised Learning

Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training

Can Transformers Learn to Solve Problems Recursively?

Language models can explain neurons in language models

Deep learning-guided discovery of an antibiotic targeting Acinetobacter baumannii

Model evaluation for extreme risks

Csa living off the land

Research Focus: Causal reasoning & LLMs, DNA data storage

LIMA: Less Is More for Alignment

RWKV: Reinventing RNNs for the Transformer Era

Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling

EdArXiv Preprints

Social Digital Cyborgs: The Collaborative Design Process of JIZAI ARMS | Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems

Inadvertent human genomic bycatch and intentional capture raise beneficial applications and ethical concerns with environmental DNA - Nature Ecology & Evolution

CHI 2023 highlights: Work and wellbeing, memory augmentation, and more

Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Enabling conversational interaction on mobile with LLMs

F-VLM: Open-vocabulary object detection upon frozen vision and language models

Behavioral changes during the COVID-19 pandemic decreased income diversity of urban encounters - Nature Communications

Language models can explain neurons in language models

Observation of anti-damping spin-orbit torques generated by in-plane and out-of-plane spin polarizations in MnPd3

Semantic reconstruction of continuous language from non-invasive brain recordings