Transformer-based networks
PulseAugur coverage of Transformer-based networks — every cluster mentioning Transformer-based networks across labs, papers, and developer communities, ranked by signal.
-
New framework analyzes similarity development in vision networks
Researchers have introduced the Deep Similarity Inspector (DSI), a novel framework designed to systematically analyze how similarity perception develops within supervised vision networks during training. This tool allow…
-
New GDBR attack breaches privacy in federated learning with partial encryption
Researchers have developed a new attack called GDBR that can recover private labels from federated learning systems that use partial gradient encryption. This attack exploits a vulnerability in neural network architectu…
-
New methodology speeds up design of photonic AI accelerators
Researchers have developed DxPTA, a new methodology for designing photonic transformer accelerators (PTAs). This approach uses optical dataflow to guide hardware and software co-design, addressing limitations of previou…
-
Sakana AI's DiffusionBlocks cuts training memory by training network blocks independently
Sakana AI has introduced DiffusionBlocks, a novel framework for training neural networks more efficiently. This method partitions a network into multiple blocks, allowing each block to be trained independently. By reduc…