Yaroslav Aksenov
PulseAugur coverage of Yaroslav Aksenov — every cluster mentioning Yaroslav Aksenov across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New LIMe extension boosts Transformer representation capacity
Researchers have introduced Layer-Integrated Memory (LIMe), a novel extension for Transformer models designed to enhance their representation capacity. Unlike traditional Transformers that rely solely on the previous la…
-
New Soft Latent Thinking method improves LLM reasoning in continuous space
Researchers have introduced Soft Latent Thinking, a novel method designed to enhance the reasoning capabilities of large language models. This approach replaces the traditional computational head used for decoding with …
-
New KronSAE design enhances sparse autoencoder efficiency and interpretability
Researchers have introduced KronSAE, a novel design for Sparse Autoencoders (SAEs) that improves their efficiency and interpretability. Unlike traditional SAEs that treat latent dictionaries as flat coordinates, KronSAE…