Neighborhood Guided Efficient Autoregressive Set Transformer
PulseAugur coverage of Neighborhood Guided Efficient Autoregressive Set Transformer — every cluster mentioning Neighborhood Guided Efficient Autoregressive Set Transformer across labs, papers, and developer communities, ranked by signal.
-
AI agents coordinate electric delivery fleet charging without central control · 2 sources tracked
Researchers have developed a novel approach for coordinating charging in electric delivery fleets using learning agents under local control. These agents, running the same policy on each vehicle, make independent decisi…
-
AI models advance 3D molecular generation for drug discovery
Two new research papers introduce advanced AI models for 3D molecular generation. The first, Equivariant-Free Transformer-Autoencoded Latent Flow Matching (EF-TALFM), uses a fixed-dimensional latent representation to ge…
-
ES-HyperNEAT hyperparameter optimization using TPE shows promise
A new study explores optimizing hyperparameters for ES-HyperNEAT, a neuroevolutionary algorithm, using the Tree-structured Parzen Estimator (TPE) approach. The research investigated over 3 billion hyperparameter combina…
-
New EMR-HyperNEAT method accelerates neuroevolution with tensorization
Researchers have developed EMR-HyperNEAT, a novel approach to neuroevolution that significantly accelerates the process of evolving large-scale neural network substrates. This new method overcomes limitations of previou…
-
AI agents evolve complex structures without fitness functions
Researchers have developed a new platform called Genesis that allows for the evolution of self-organizing agents without relying on a designer-specified fitness function. Through three experimental cycles, they demonstr…
-
New AI methods optimize analog circuit design with improved efficiency and reliability · 3 sources tracked
Two new research papers introduce novel methods for optimizing analog circuits. Lighthouse RL employs a sample-efficient reinforcement learning approach with strategic reset points to improve performance and generalizat…
-
Seq103 framework discovers compact sequence architectures with less parameters
Researchers have developed Seq103, a novel neuroevolution framework designed to discover compact sequence architectures. This unified system utilizes a shared evolutionary backbone with an optional recurrent extension t…
-
NEAT transformer generates 3D molecules with state-of-the-art speed and accuracy
Researchers have developed NEAT, a novel autoregressive set transformer designed for 3D molecular generation. Unlike previous methods that rely on sequential atom ordering, NEAT treats molecules as sets and uses a neigh…
-
Think Anywhere in Code Generation
Researchers have introduced "Think-Anywhere," a new reasoning mechanism for large language models that allows them to generate code by thinking at any point during the process, rather than just upfront. This approach ha…