10.9k citations
- Massachusetts Institute of TechnologyUS270 papers
- Harvard UniversityUS238 papers
- The Ohio State UniversityUS186 papers
- Lawrence Berkeley National LaboratoryUS185 papers
- University of OxfordGB176 papers
- University of PisaIT169 papers
- University of ChicagoUS168 papers
- University of LiverpoolGB167 papers
- University of MichiganUS166 papers
- Sapienza University of RomeIT165 papers
- Yale UniversityUS160 papers
- University of Wisconsin–MadisonUS155 papers
120 papers · 1 filter
Closing the Loop: Formally Verified Law as a Reward Signal for Self-Improving Legal AI
Armin Heydari, Torben Leowald
This article develops an architecture that creates a formally verifiable reward signal to train legal AI, adapting the LLM proposes, verifier disposes paradigm from mathematical AI…
DynamiQ: Accelerating Gradient Synchronization using Compressed Multi-hop All-reduce
Wenchen Han, Shay Vargaftik, Michael Mitzenmacher +1
Multi-hop all-reduce is the de facto backbone of large model training. As the training scale increases, the network often becomes a bottleneck, motivating the reduction of the volu…
Deep Neural Networks as Discrete Dynamical Systems: Implications for Physics-Informed Learning
Abhisek Ganguly, Santosh Ansumali, Sauro Succi
We revisit the analogy between feed-forward deep neural networks (DNNs) and discrete dynamical systems derived from neural integral equations and their corresponding partial differ…
Adaptive EEG-based stroke diagnosis with a GRU-TCN classifier and deep Q-learning thresholding
Shakeel Abdulkareem, Bora Yimenicioglu, Khartik Uppalapati +3
Rapid triage of suspected stroke needs accurate, bedside-deployable tools; EEG is promising but underused at first contact. We present an adaptive multitask EEG classifier that con…
Analyzing Political Text at Scale with Online Tensor LDA
Sara Kangaslahti, Danny Ebanks, Jean Kossaifi +3
This paper proposes a topic modeling method that scales linearly to billions of documents. We make three core contributions: i) we present a topic modeling method, Tensor Latent Di…
Reinforcement Learning Closures for Underresolved Partial Differential Equations using Synthetic Data
Lothar Heimbach, Sebastian Kaltenbach, Petr Karnakov +2
Partial Differential Equations (PDEs) describe phenomena ranging from turbulence and epidemics to quantum mechanics and financial markets. Despite recent advances in computational…