Radio ffn
PulseAugur coverage of Radio ffn — every cluster mentioning Radio ffn across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New Mobius-v0 architecture decouples knowledge and reasoning for faster AI inference
Researchers have introduced Mobius-v0, a novel foundation model architecture that decouples knowledge storage from reasoning processes. This design utilizes a shared memory component for knowledge vectors and multiple r…
-
New MoE methods enhance federated LLM tuning for private data
Researchers have developed new methods for federated instruction tuning of Mixture-of-Experts (MoE) Large Language Models (LLMs) to handle decentralized and private data. One approach, ClientMorpher, uses MoE router sig…
-
Research paper reveals FFNs actively steer long-context retrieval
A new research paper explores the role of Feed-Forward Networks (FFNs) in long-context retrieval tasks, moving beyond their traditional view as parametric memories. The study demonstrates that FFNs actively influence th…
-
DomLoRA method places single adapter at dominant module for efficient fine-tuning
Researchers have developed a new method called DomLoRA for parameter-efficient fine-tuning of large language models. This technique identifies a single "dominant adaptation module" within a model where placing a low-ran…
-
State Stream Transformer V2 enhances LLM reasoning with parallel training and latent state streaming
Researchers have developed the State Stream Transformer (SST) V2, an architectural innovation designed to enhance latent space reasoning in language models. Unlike standard transformers that reset context at each step, …
-
New diagnostic tool probes LLM circuits for safety and behavior insights
A new research paper introduces "Perturbation Probing," a diagnostic method for understanding the internal workings of large language models. This technique uses two forward passes per prompt to identify and analyze "be…
-
Hugging Face introduces Graph Memory Transformer replacing FFNs with learned memory graphs
Researchers have developed a Graph Memory Transformer (GMT) that replaces the standard Feed-Forward Network (FFN) sublayer in decoder-only transformers with an explicit learned memory graph. This new architecture mainta…
-
Graph Memory Transformer replaces FFNs with learned memory graphs for interpretability
Researchers have developed a Graph Memory Transformer (GMT) that replaces the standard Feed-Forward Network (FFN) sublayer in decoder-only language models with an explicit learned memory graph. This new architecture, GM…