Selfies
PulseAugur coverage of Selfies — every cluster mentioning Selfies across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New SIGMA objective improves molecular autoregressive models
Researchers have developed SIGMA, a novel objective for autoregressive molecular models that improves their ability to assign probabilities to molecules regardless of their serialization format. This method uses a dense…
-
UniPolymer framework streamlines polyimide design with AI
Researchers have developed UniPolymer, a novel framework designed to streamline the process of designing polyimide structures with specific glass transition temperatures (Tg). This unified system integrates property pre…
-
SpectralMol algorithm uses Fourier coefficients for molecular generation
Researchers have developed SpectralMol, a novel algorithm that utilizes evolutionary computation and Fourier coefficients to generate molecular structures. This method processes chemical structures as a matrix of Fourie…
-
BioMatrix integrates sequences, structures, and language in new multimodal foundation model
Researchers have developed BioMatrix, a novel multimodal foundation model designed to integrate biological data types like sequences, structures, and natural language within a single architecture. Unlike previous models…
-
DriftingMol framework enhances property-conditional molecular generation
Researchers have developed DriftingMol, a novel two-stage framework for generating molecules with specific properties. This method adapts drifting models to a SELFIES latent molecular space, utilizing the decoder's hidd…
-
AI can extract fingerprints from high-res selfies, experts warn
Artificial intelligence may be capable of extracting usable fingerprint data from high-resolution selfies, according to security experts. This could pose a significant privacy risk, as such images, if taken from a close…
-
AI model learns chemical properties from molecular data, controlling for sequence shortcuts
Researchers have developed a new method to evaluate molecular generative models, specifically Transformer-VAEs trained on SELFIES. Their approach addresses the issue where apparent property predictability might stem fro…